INDEX

Explanations

enum or type properties

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

enum-like constructs or property/method identifiers in programming code, particularly when they appear with dot notation or as part of type specifications.

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

This neuron fires on references to enumeration or other named constant members (e.g. EnumType.Member) in code.

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

"}}>

-1.59

薬品

-1.36

鬭

-1.32

ÑA

-1.31

 fashioned

-1.30

 they

-1.30

 tirantes

-1.27

ώ

-1.26

（

-1.26

));

-1.26

POSITIVE LOGITS

he

1.62

 OTHER

1.52

ucksack

1.43

潆

1.38

THERE

1.27

荽

1.26

 nokt

1.25

Others

1.23

蕻

1.23

kken

1.23

Activations Density 0.004%

enum or type properties

enum-like constructs or property/method identifiers in programming code, particularly when they appear with dot notation or as part of type specifications.

This neuron fires on references to enumeration or other named constant members (e.g. EnumType.Member) in code.

No Comments

No Known Activations

enum or type properties

enum-like constructs or property/method identifiers in programming code, particularly when they appear with dot notation or as part of type specifications.

This neuron fires on references to enumeration or other named constant members (e.g. EnumType.Member) in code.

No Comments

No Known Activations