INDEX

Explanations

vector graphics and network analyzer

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

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vetmediation”).

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

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ắ

0.63

 spad

0.61

 Honestly

0.59

ремен

0.58

 ज्यामुळे

0.57

валися

0.54

метри

0.54

Honestly

0.54

enderita

0.53

tmpobj

0.53

POSITIVE LOGITS

Ve

0.64

Veter

0.63

Ved

0.59

Ve

0.59

Vé

0.59

nesday

0.58

 vect

0.57

 likelihood

0.57

aved

0.56

Funk

0.55

Activations Density 0.212%

vector graphics and network analyzer

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vetmediation”).

No Comments

No Known Activations

vector graphics and network analyzer

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vetmediation”).

No Comments

No Known Activations

vector graphics and network analyzer

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vet­mediation”).

No Comments

No Known Activations

vector graphics and network analyzer

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vet­mediation”).

No Comments

No Known Activations

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vetmediation”).

The neuron is activated by tokens beginning with the letter sequence “Ve” (e.g. “Vector,” “Vetráz,” “Venoms,” “Vetmediation”).