INDEX

Explanations

root of directory or project

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

the word "root" in code comments and technical documentation, especially when referring to root directories or root-level project structures.

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

The neuron fires on occurrences of the token “root,” especially when it’s used to refer to a root directory, namespace, or project root.

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

氿

-1.90

LayoutConstraint

-1.73

⩴

-1.66

 nossos

-1.52

 устанавли

-1.49

itettura

-1.48

 Añade

-1.45

鲞

-1.43

が出て

-1.39

応え

-1.38

POSITIVE LOGITS

of

2.11

 there

1.97

 retrato

1.84

┍

1.77

初の

1.66

この日

1.65

 paraíso

1.61

although

1.60

most

1.59

 cromado

1.59

Activations Density 0.033%

root of directory or project

the word "root" in code comments and technical documentation, especially when referring to root directories or root-level project structures.

The neuron fires on occurrences of the token “root,” especially when it’s used to refer to a root directory, namespace, or project root.

No Comments

No Known Activations

root of directory or project

the word "root" in code comments and technical documentation, especially when referring to root directories or root-level project structures.

The neuron fires on occurrences of the token “root,” especially when it’s used to refer to a root directory, namespace, or project root.

No Comments

No Known Activations