INDEX

Explanations

numbers, indices, positions

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

The neuron is primarily detecting numeric literals (especially floating‐point numbers).

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

line breaks or newlines in code or technical documentation.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

code comment and documentation sections within source code or technical scripts

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_24_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

be

0.23

so

0.23

of

0.22

↵↵

0.21

are

0.21

že

0.20

 Americana

0.20

 jiné

0.20

in

0.20

do

0.20

POSITIVE LOGITS

SanPham

0.24

ヘ

0.24

YAML

0.23

 ニット

0.22

رسٹ

0.22

 ))->

0.22

OUBLE

0.22

пили

0.21

╽

0.21

ヤモンド

0.21

Activations Density 0.003%

numbers, indices, positions

The neuron is primarily detecting numeric literals (especially floating‐point numbers).

line breaks or newlines in code or technical documentation.

code comment and documentation sections within source code or technical scripts

No Comments

No Known Activations

numbers, indices, positions

The neuron is primarily detecting numeric literals (especially floating‐point numbers).

line breaks or newlines in code or technical documentation.

code comment and documentation sections within source code or technical scripts

No Comments

No Known Activations