INDEX

Explanations

code class definitions

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

class declarations in programming code.

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

The neuron flags type‐definition tokens in code—e.g. class and struct declarations and their 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

 there

-1.72

you

-1.44

があります

-1.40

 некоторые

-1.36

Are

-1.30

ara

-1.30

 several

-1.28

zczy

-1.28

 irgend

-1.28

 some

-1.27

POSITIVE LOGITS

 ideen

1.64

uniqlo

1.59

 sudah

1.53

versace

1.50

olge

1.48

jaket

1.47

ата

1.45

 ПРЕ

1.43

replyreport

1.38

tvguide

1.38

Activations Density 0.055%

code class definitions

class declarations in programming code.

The neuron flags type‐definition tokens in code—e.g. class and struct declarations and their names.

No Comments

No Known Activations

code class definitions

class declarations in programming code.

The neuron flags type‐definition tokens in code—e.g. class and struct declarations and their names.

No Comments

No Known Activations