INDEX

Explanations

hexadecimal characters and numbers

np_acts-logits-general · gemini-2.5-flash-lite

hexadecimal color codes and memory addresses (values starting with 'f' followed by digits or letters in hex format).

oai_token-act-pair · claude-4-5-sonnet

Triggered by @bfgcn7frf5

This neuron detects hexadecimal digits (0–9, a–f) occurring in hex literals (e.g. color codes or 0x… constants).

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

how

-1.77

 jesteśmy

-1.61

itieren

-1.59

全体の

-1.47

ktı

-1.44

⃙

-1.42

⚋

-1.42

requisite

-1.42

 asig

-1.41

 būti

-1.40

POSITIVE LOGITS

or

1.84

1.73

was

1.70

↵↵

1.70

1.63

 They

1.63

 same

1.61

you

1.58

 genannten

1.57

plugins

1.56

Activations Density 0.017%

hexadecimal characters and numbers

hexadecimal color codes and memory addresses (values starting with 'f' followed by digits or letters in hex format).

This neuron detects hexadecimal digits (0–9, a–f) occurring in hex literals (e.g. color codes or 0x… constants).

No Known Activations

hexadecimal characters and numbers

hexadecimal color codes and memory addresses (values starting with 'f' followed by digits or letters in hex format).

This neuron detects hexadecimal digits (0–9, a–f) occurring in hex literals (e.g. color codes or 0x… constants).

No Known Activations