INDEX

Explanations

data model classes

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

the word "Model" when it appears in programming code, particularly in class names and type declarations.

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

The neuron fires on the identifier “Model” (e.g. class or property names containing “Model”) in code snippets.

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

 particularly

-1.92

 especially

-1.89

not

-1.61

 first

-1.48

my

-1.47

 even

-1.45

in

-1.35

 primeras

-1.29

at

-1.27

or

-1.26

POSITIVE LOGITS

üenza

1.62

躋

1.44

Zutaten

1.44

seminar

1.39

在這

1.37

 considérons

1.36

ってしまう

1.35

crème

1.34

 استناد

1.33

 mortos

1.31

Activations Density 0.009%

data model classes

the word "Model" when it appears in programming code, particularly in class names and type declarations.

The neuron fires on the identifier “Model” (e.g. class or property names containing “Model”) in code snippets.

No Comments

No Known Activations

data model classes

the word "Model" when it appears in programming code, particularly in class names and type declarations.

The neuron fires on the identifier “Model” (e.g. class or property names containing “Model”) in code snippets.

No Comments

No Known Activations