INDEX

Explanations

programming contexts and bios

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

colons that introduce or follow labels, metadata fields, or section headers in structured text and code.

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

This neuron responds strongly to code- and markup-specific tokens—e.g. function/module names, object property identifiers, and HTML tag names.

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

you

-1.34

 your

-1.30

 не

-1.28

Ꮪ

-1.24

pylene

-1.24

SaveChangesAsync

-1.22

而

-1.22

 через

-1.20

 производстве

-1.19

 quotidienne

-1.18

POSITIVE LOGITS

and

1.71

 olvidar

1.45

 encontr

1.43

how

1.35

殽

1.34

 când

1.30

 descansar

1.28

 acudir

1.24

 comprender

1.21

Activations Density 0.003%

programming contexts and bios

colons that introduce or follow labels, metadata fields, or section headers in structured text and code.

This neuron responds strongly to code- and markup-specific tokens—e.g. function/module names, object property identifiers, and HTML tag names.

No Comments

No Known Activations

programming contexts and bios

colons that introduce or follow labels, metadata fields, or section headers in structured text and code.

This neuron responds strongly to code- and markup-specific tokens—e.g. function/module names, object property identifiers, and HTML tag names.

No Comments

No Known Activations