INDEX

Explanations

code snippets or comments

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

Java package imports and namespace declarations in source code.

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

The neuron fires on code‐style dotted identifiers and import/package declarations (e.g. Java or XML namespace paths).

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

Tienen

-1.73

 récord

-1.70

 сообщили

-1.60

ײ

-1.57

œuf

-1.56

Breite

-1.53

 obfer

-1.48

 menegaskan

-1.48

 Spéc

-1.47

 gastronomía

-1.46

POSITIVE LOGITS

 иногда

1.63

 such

1.58

 material

1.39

1.37

 изображения

1.35

 パソコン

1.30

 掃除

1.30

we

1.27

 недорого

1.25

is

1.24

Activations Density 0.005%

code snippets or comments

Java package imports and namespace declarations in source code.

The neuron fires on code‐style dotted identifiers and import/package declarations (e.g. Java or XML namespace paths).

No Comments

No Known Activations

code snippets or comments

Java package imports and namespace declarations in source code.

The neuron fires on code‐style dotted identifiers and import/package declarations (e.g. Java or XML namespace paths).

No Comments

No Known Activations