the word 'human' in science text

What this neuron does

This neuron lights up on the word 'human' when it appears in medical and biology writing, such as 'human tumors' or 'human cells'. Turning it up made the model's output drift toward unrelated text and did not produce a clear theme.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

1. #1 peak

   pathogens. Low doses of CpG injected into a tumor induce the expression of OX40 on CD4+ T cells in the microenvironment in mouse or human tumors. An agonistic anti-OX40 antibody can then trigger a T

2. #2 peak

   into both neurons, which extended axons into the host spinal cord over remarkably long distances, and glia. Grafts of cultured human NSCs expressing GFP resulted in similar findings. Thus, methods are defined for improving

3. #3 peak

   Fig. 1. Electron microscopy of the viral-like particles generated by the Phoenix provirus transfected into human 293T cells. The prominent spikes of the Env protein are visible

4. #4 peak

   istochemical of paraffin-embedded human ovary tumor using 10201-2-AP (ub

5. #5 peak

   Norris Cotton Cancer Center (NCCC) Mechanism Research Program.⏎There is a lack of mouse cell lines that harbor the BRAF mutation that is so prevalent in human melanomas, and the cell lines that are available grow slowly in culture and are

6. #6 peak

   of each patient's tumor and to develop new therapeutic targets.⏎In their study, Kim and her colleagues looked at mouse models of the three most commonly mutated genes in human lung cancer -- K-RAS and p53 (two genes predominantly mutated in

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

1. #1 peak

   ackles, European starlings, American robins and house sparrows appear to be the most affected.⏎"Transmission electron microscopy and additional diagnostic tests, including microbiology, virology, parasitology and toxicology are ongoing," the Kentucky

2. #2 peak

   tools to measure whether the intervention or medication works. A new study by researchers at the UC Davis MIND Institute and other institutions suggests that the NIH Toolbox Cognition Battery (NIHTB-CB) is a promising option. The study found the

3. #3 peak

   detect biomolecules of interest without requiring the additional use of an optical label. They used a tightly focused laser to drill holes through a 100-nanometer-thick layer of gold deposited on a 100-nanometer-th

4. #4 peak

   efforts, SFWMD field crews constructed a 140-foot weir and flow-way channel to move water from the J.W. Corbett Wildlife

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.