INDEX

Explanations

biological signaling and approximations

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

mathematical approximation symbols like "≈" and "≡" used to indicate rough equivalence.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron strongly activates on standalone numeric tokens (including integers and decimal numbers).

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

-3.55

-2.95

-2.56

-2.47

We

-2.33

The

-2.28

-2.27

-2.25

 WITHOUT

-2.23

之后

-2.22

POSITIVE LOGITS

銪

2.83

蟶

2.63

ization

2.58

꜆

2.56

 土産

2.53

闿

2.52

珧

2.47

acterísticas

2.47

淶

2.47

 cheminée

2.45

Activations Density 0.001%

biological signaling and approximations

mathematical approximation symbols like "≈" and "≡" used to indicate rough equivalence.

The neuron strongly activates on standalone numeric tokens (including integers and decimal numbers).

No Comments

No Known Activations

biological signaling and approximations

mathematical approximation symbols like "≈" and "≡" used to indicate rough equivalence.

The neuron strongly activates on standalone numeric tokens (including integers and decimal numbers).

No Comments

No Known Activations