INDEX

Explanations

`def` followed by function parameters

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

documentation comments and function/class definitions in code, particularly markers like `@param`, `"""`, `A:`, and `func`.

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

The neuron fires on documentation‐style comment annotations (e.g. tags beginning with “@” like @param, @returns, @example, and the closing “*/”).

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

 there

-2.28

its

-1.82

 created

-1.45

it

-1.41

in

-1.39

 also

-1.34

 dieses

-1.33

colos

-1.30

 still

-1.30

 Arbeitnehmer

-1.30

POSITIVE LOGITS

 specta

1.46

 userDao

1.45

 despi

1.40

⾞

1.40

 حتی

1.38

 sogar

1.32

 навіть

1.31

 pérd

1.30

 ステン

1.30

 premat

1.29

Activations Density 0.105%

`def` followed by function parameters

documentation comments and function/class definitions in code, particularly markers like `@param`, `"""`, `A:`, and `func`.

The neuron fires on documentation‐style comment annotations (e.g. tags beginning with “@” like @param, @returns, @example, and the closing “*/”).

No Comments

No Known Activations

`def` followed by function parameters

documentation comments and function/class definitions in code, particularly markers like `@param`, `"""`, `A:`, and `func`.

The neuron fires on documentation‐style comment annotations (e.g. tags beginning with “@” like @param, @returns, @example, and the closing “*/”).

No Comments

No Known Activations