INDEX

Explanations

cultures thereof

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

numeric values and metadata in code or technical documentation.

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

The neuron is primarily sensitive to tokens containing digits (i.e. numeric literals).

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/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

utkan

-0.69

atores

-0.68

Titel

-0.68

Aza

-0.68

हाय

-0.67

 وضع

-0.66

 russ

-0.65

 symphon

-0.64

Objectives

-0.63

мать

-0.63

POSITIVE LOGITS

.${

0.85

 dạ

0.77

literally

0.77

三人

0.77

 kilka

0.76

 деревня

0.75

 duża

0.74

rupt

0.74

 hạ

0.73

嗪

0.73

Activations Density 0.046%

cultures thereof

numeric values and metadata in code or technical documentation.

The neuron is primarily sensitive to tokens containing digits (i.e. numeric literals).

No Comments

No Known Activations

cultures thereof

numeric values and metadata in code or technical documentation.

The neuron is primarily sensitive to tokens containing digits (i.e. numeric literals).

No Comments

No Known Activations