INDEX

Explanations

Listing, health, or post data

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

function parameters in programming code, particularly focusing on method signatures with their argument lists.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron fires on programming identifiers—variable, function, and parameter names (and similar code tokens)—rather than ordinary prose.

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



-1.25

恭喜

-1.23

depends

-1.23

 connue

-1.22

 várias

-1.22

 Lösungen

-1.19

 vários

-1.18

 PARTICULAR

-1.17

 سنوات

-1.17

 العديد

-1.17

POSITIVE LOGITS

 that

1.75

 this

1.41

huo

1.38

one

1.35

 only

1.27

 sali

1.24

 dolorosa

1.23

 which

1.23

 gallina

1.21

 Politica

1.19

Activations Density 0.146%

Listing, health, or post data

function parameters in programming code, particularly focusing on method signatures with their argument lists.

The neuron fires on programming identifiers—variable, function, and parameter names (and similar code tokens)—rather than ordinary prose.

No Comments

No Known Activations

Listing, health, or post data

function parameters in programming code, particularly focusing on method signatures with their argument lists.

The neuron fires on programming identifiers—variable, function, and parameter names (and similar code tokens)—rather than ordinary prose.

No Comments

No Known Activations