INDEX

Explanations

programming keywords

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

code tokens in object-oriented programming contexts, particularly related to classes, objects, methods, and API structures.

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

This neuron fires on programming-language import, require, or include statements (i.e. lines that bring in external modules or libraries).

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

of

-1.91

-1.57

or

-1.45

to

-1.23

unless

-1.18

if

-1.15

-1.12

and

-1.09

 either

-1.09

POSITIVE LOGITS

 apoyo

1.29

www

1.27

 pingente

1.25

ὼ

1.25

 solches

1.24

xian

1.21

 drenaje

1.20

 lámparas

1.20

Sementara

1.20

 muñeco

1.19

Activations Density 0.078%

programming keywords

code tokens in object-oriented programming contexts, particularly related to classes, objects, methods, and API structures.

This neuron fires on programming-language import, require, or include statements (i.e. lines that bring in external modules or libraries).

No Comments

No Known Activations

programming keywords

code tokens in object-oriented programming contexts, particularly related to classes, objects, methods, and API structures.

This neuron fires on programming-language import, require, or include statements (i.e. lines that bring in external modules or libraries).

No Comments

No Known Activations