INDEX

Explanations

android development

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

the word "android" in code and XML files.

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

The neuron strongly fires on occurrences of the token “android” (e.g. in XML namespaces, package names, support‐library coordinates, SDK attributes, etc.).

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

ють

-1.86

rowing

-1.72

㩒

-1.63

 beş

-1.55

ↀ

-1.53

Nacimiento

-1.44

 aqueles

-1.41

 Spanien

-1.40

Cull

-1.40



-1.39

POSITIVE LOGITS

This

2.05

Thus

1.95

Also

1.93

祧

1.88

1.80

Basically

1.71

Therefore

1.69

1.66

Here

1.63

Too

1.63

Activations Density 0.010%

android development

the word "android" in code and XML files.

The neuron strongly fires on occurrences of the token “android” (e.g. in XML namespaces, package names, support‐library coordinates, SDK attributes, etc.).

No Comments

No Known Activations

android development

the word "android" in code and XML files.

The neuron strongly fires on occurrences of the token “android” (e.g. in XML namespaces, package names, support‐library coordinates, SDK attributes, etc.).

No Comments

No Known Activations