INDEX

Explanations

programming functions declaration

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

This neuron detects Python “from future import” feature‐enabling 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

檍

-1.40

 regering

-1.38

拊

-1.36

鼉

-1.36

^,

-1.30

 ſta

-1.29

 chini

-1.28

topi

-1.27

 yake

-1.27

it

-1.26

POSITIVE LOGITS

('

1.32

vency

1.23

1.20

but

1.20

 nutrición

1.20

 místě

1.19

!!

1.18

 again

1.15

寺の

1.15

1.13

Activations Density 0.073%

programming functions declaration

This neuron detects Python “from future import” feature‐enabling import statements.

No Comments

No Known Activations

programming functions declaration

This neuron detects Python “from future import” feature‐enabling import statements.

No Comments

No Known Activations

programming functions declaration

This neuron detects Python “from __future__ import” feature‐enabling import statements.

No Comments

No Known Activations

programming functions declaration

This neuron detects Python “from __future__ import” feature‐enabling import statements.

No Comments

No Known Activations

This neuron detects Python “from future import” feature‐enabling import statements.

This neuron detects Python “from future import” feature‐enabling import statements.