INDEX

Explanations

code blocks

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

function definitions in programming code, specifically at the closing parenthesis before the opening brace.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron fires on the Go testing framework’s function signatures—specifically the “*testing.T” parameter token in TestXxx definitions.

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

Not in Any Lists

No Comments

Negative Logits

and

-1.93

陆续

-1.77

 书法

-1.76

驍

-1.63

 الطفل

-1.61

𝙪

-1.54

𝟏

-1.52

-1.50

reggio

-1.48

手続き

-1.47

POSITIVE LOGITS

 where

1.84

in

1.55

ia

1.52

io

1.50

 they

1.49

ed

1.47

PvB

1.46

ne

1.44

 utilizada

1.43

乆

1.41

Activations Density 0.007%

code blocks

function definitions in programming code, specifically at the closing parenthesis before the opening brace.

The neuron fires on the Go testing framework’s function signatures—specifically the “*testing.T” parameter token in TestXxx definitions.

No Comments

No Known Activations

code blocks

function definitions in programming code, specifically at the closing parenthesis before the opening brace.

The neuron fires on the Go testing framework’s function signatures—specifically the “*testing.T” parameter token in TestXxx definitions.

No Comments

No Known Activations