INDEX

Explanations

programming model

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

the word "model" in code, particularly in package declarations and import statements.

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

The neuron activates on occurrences of the token “model” (e.g. in package, import, class, or XML element 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

we

-2.64

↵

-2.41

 wenige

-2.39

AutoresizingMask

-2.22

 grim

-2.22

潆

-2.20

訁

-2.17

檬

-2.16

 使っ

-2.14

 lose

-2.06

POSITIVE LOGITS

the

3.73



3.06

婓

2.94

婞

2.80

2.73

᯾

2.66

The

2.63

 kapsul

2.55

They

2.53

 keramik

2.50

Activations Density 0.005%

programming model

the word "model" in code, particularly in package declarations and import statements.

The neuron activates on occurrences of the token “model” (e.g. in package, import, class, or XML element names).

No Comments

No Known Activations

programming model

the word "model" in code, particularly in package declarations and import statements.

The neuron activates on occurrences of the token “model” (e.g. in package, import, class, or XML element names).

No Comments

No Known Activations