INDEX

Explanations

code imports from libraries

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

The neuron flags import paths that reference scoped (“@…”) npm package names in import statements.

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

酲

-2.44

 signifikan

-2.08

 花卉

-2.05

蹌

-1.95

 красивый

-1.93

 hoping

-1.91

fying

-1.91

蔟

-1.86

☫

-1.84

POSITIVE LOGITS

 impos

2.27

 facile

2.13

 monument

1.99

şört

1.91

god

1.85

 Spielen

1.82

 entrepreneur

1.80

ᨁ

1.80

 этом

1.78

 podemos

1.78

Activations Density 0.002%

code imports from libraries

The neuron flags import paths that reference scoped (“@…”) npm package names in import statements.

No Comments

No Known Activations

code imports from libraries

The neuron flags import paths that reference scoped (“@…”) npm package names in import statements.

No Comments

No Known Activations

code imports from libraries

The neuron flags import paths that reference scoped (​“@…”​) npm package names in import statements.

No Comments

No Known Activations

code imports from libraries

The neuron flags import paths that reference scoped (​“@…”​) npm package names in import statements.

No Comments

No Known Activations

The neuron flags import paths that reference scoped (“@…”) npm package names in import statements.

The neuron flags import paths that reference scoped (“@…”) npm package names in import statements.