INDEX

Explanations

introduction to study or code

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

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “main”, “<module>”, “True”).

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

 همچنین

-1.27

 memiliki

-1.24

 valamint

-1.17

 illuminate

-1.15

ignée

-1.13

鼍

-1.09

uristic

-1.09

 anche

-1.08

 sostu

-1.08

 menjelaskan

-1.06

POSITIVE LOGITS

1.69

zzlies

1.13

<bos>

1.09

žena

1.08

萊

1.03

↵

1.02

.”

1.00

谙

1.00

！！！！

0.98

 alpina

0.98

Activations Density 0.001%

introduction to study or code

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “main”, “<module>”, “True”).

No Comments

No Known Activations

introduction to study or code

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “main”, “<module>”, “True”).

No Comments

No Known Activations

introduction to study or code

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “__main__”, “<module>”, “True”).

No Comments

No Known Activations

introduction to study or code

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “__main__”, “<module>”, “True”).

No Comments

No Known Activations

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “main”, “<module>”, “True”).

The neuron fires strongly on Python’s special built-in identifiers and keywords (e.g. “main”, “<module>”, “True”).