the zero digit in decimals

What this neuron does

This neuron lights up on the digit 0 when it appears in a decimal or a number that starts with a zero, such as 0.99 or 0.000001. Pushing it down made the model write long runs of zeros, and pushing it up made the writing drift into unrelated topics.

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

   Fat, there are 0 grams of Trans Fat, and there are 5 grams left over.⏎Cholesterol - Watching your Cholesterol? One serving has 0 mg, which should make healthy eating a little easier.⏎Carbohydrates - Total

2. #2 peak

   terrestrial (longwave) radiation, which is centered around a wavelength of 10μm. The absorptivity and emissivity around freezing point is 0.99 – meaning that only 1% of incident longwave radiation would

3. #3 peak

   Library maintained by the Modelica Association.⏎This example demonstrates different noise distributions methods that can be selected for a Noise block. Both noise blocks use samplePeriod = 0.02 s, y_min=-1, y_max=3, and

4. #4 peak

   . Freshwater entering the major estuaries is, where not contaminated, of acceptable quality for drinking with minimum treatment. However, iron concentrations in excess of 0.

5. #5 peak

   A single heat pulse will switch the magnetic orientation of a nanometer-sized magnetic grain in just a few picoseconds (1 picosecond is 0.000000000001 seconds). As

6. #6 peak

   E, 17.3 µg of Vitamin K, 106.488 g of total saturated fat, 0.216 g of lauric acid, 2.16

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

   archive.jpr.org.uk/10.1177%2F13591045050537

2. #2 peak

   ". PLoS ONE 8 (2): e57075. . . http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.

3. #3 peak

   and%20adaptive%20immune%20system.⏎- How Vitamin C Supports a Healthy Imm

4. #4 peak

   2017, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5707683/#:~:text=It%20is%20a%20potent%20ant

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.