INDEX

Explanations

code identifiers and parameters

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

data type declarations or variable definitions in programming code, particularly for integers and data structures.

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

The neuron is looking for code identifiers (e.g. function or type names) rather than ordinary words.

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

 There

-3.22

When

-2.94

تیجه

-2.70

There

-2.61

with

-2.48

How

-2.48

’

-2.45

Then

-2.44

These

-2.44

ၞ

-2.31

POSITIVE LOGITS

趼

2.86

婓

2.83



2.75

 FontWeight

2.70

驺

2.56

豨

2.53

 juſ

2.48

嚶

2.44

⤥

2.42

⮑

2.41

Activations Density 0.001%

code identifiers and parameters

data type declarations or variable definitions in programming code, particularly for integers and data structures.

The neuron is looking for code identifiers (e.g. function or type names) rather than ordinary words.

No Comments

No Known Activations

code identifiers and parameters

data type declarations or variable definitions in programming code, particularly for integers and data structures.

The neuron is looking for code identifiers (e.g. function or type names) rather than ordinary words.

No Comments

No Known Activations