INDEX

Explanations

code or quoted strings

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

string literals in programming code, particularly those opening quotes that begin string assignments or declarations.

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

This neuron detects string literals, i.e. text enclosed in quotes.

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

 podido

-1.66

or

-1.53

 depósitos

-1.47

 теперь

-1.46

 refrigerador

-1.41

 habido

-1.40

 suplementos

-1.39

࿚

-1.38

 logrado

-1.35

 toalla

-1.34

POSITIVE LOGITS

1.97

1.76

1.72

www

1.68

 leſs

1.58

ちん

1.51

 stattfinden

1.43

1.41

*/}

1.40

還要

1.40

Activations Density 0.022%

code or quoted strings

string literals in programming code, particularly those opening quotes that begin string assignments or declarations.

This neuron detects string literals, i.e. text enclosed in quotes.

No Comments

No Known Activations

code or quoted strings

string literals in programming code, particularly those opening quotes that begin string assignments or declarations.

This neuron detects string literals, i.e. text enclosed in quotes.

No Comments

No Known Activations