INDEX

Explanations

array map functions

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

arrow function syntax in code, particularly the `=>` operator and its surrounding context.

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

The neuron fires on the “=>” arrow token (used in arrow functions or JSX expressions).

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

or

-1.66

 only

-1.42

 first

-1.27

 even

-1.23

all

-1.13

这一切

-1.08

or

-1.06

 departe

-1.05

veck

-1.05

 всю

-1.04

POSITIVE LOGITS

 different

1.59

ᐕ

1.52

are

1.46

different

1.45

 различные

1.35

causing

1.34

 distintas

1.32

 különböző

1.30

varying

1.30

various

1.29

Activations Density 0.012%

array map functions

arrow function syntax in code, particularly the `=>` operator and its surrounding context.

The neuron fires on the “=>” arrow token (used in arrow functions or JSX expressions).

No Comments

No Known Activations

array map functions

arrow function syntax in code, particularly the `=>` operator and its surrounding context.

The neuron fires on the “=>” arrow token (used in arrow functions or JSX expressions).

No Comments

No Known Activations