INDEX

Explanations

function arguments

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

The neuron is highly activated by numeric literal tokens in source code.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

opening parentheses in function definitions and function calls across various programming languages.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

the opening parenthesis that starts a parameter list in code, i.e., the argument list of function/method calls or declarations across languages.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

 informace

-1.23

 những

-1.14

 usados

-1.05

 trouxe

-1.04

 zahlreiche

-1.01

 пальто

-1.00

_________

-0.97

 sessão

-0.97

 denselben

-0.96

鴒

-0.96

POSITIVE LOGITS

our

1.00

by

0.97

人で

0.94

 появится

0.91

னி

0.88

 една

0.87

きましょう

0.87

حيات

0.86

 coreana

0.85

or

0.85

Activations Density 0.006%

function arguments

The neuron is highly activated by numeric literal tokens in source code.

opening parentheses in function definitions and function calls across various programming languages.

the opening parenthesis that starts a parameter list in code, i.e., the argument list of function/method calls or declarations across languages.

No Comments

No Known Activations

function arguments

The neuron is highly activated by numeric literal tokens in source code.

opening parentheses in function definitions and function calls across various programming languages.

the opening parenthesis that starts a parameter list in code, i.e., the argument list of function/method calls or declarations across languages.

No Comments

No Known Activations