INDEX

Explanations

id= or id_

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

the word "id" in code contexts, particularly as a variable, property, or database field name.

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

The neuron specifically fires on occurrences of the literal token “id” in code (e.g. property or column 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

嘍

-1.52

the

-1.51

 любы

-1.41

ون

-1.41

 eleições

-1.38

َ

-1.38

 такие

-1.34

 Gemeinder

-1.29

 хорошая

-1.27

czerw

-1.27

POSITIVE LOGITS

<bos>

1.59

簣

1.57

 chimique

1.54

'}),

1.52

='.$

1.49

 المالية

1.46

 COUNTRIES

1.41

 végét

1.38

😫

1.37

椟

1.36

Activations Density 0.014%

id= or id_

the word "id" in code contexts, particularly as a variable, property, or database field name.

The neuron specifically fires on occurrences of the literal token “id” in code (e.g. property or column names).

No Comments

No Known Activations

id= or id_

the word "id" in code contexts, particularly as a variable, property, or database field name.

The neuron specifically fires on occurrences of the literal token “id” in code (e.g. property or column names).

No Comments

No Known Activations