INDEX

Explanations

Python special methods and OOP

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

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. init, str, get, set).

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

,'

-0.99

লা

-0.94

FFFF

-0.91

фора

-0.89

 Ouverture

-0.88

托

-0.86

פל

-0.86

רְ

-0.85

 文化

-0.85

ęki

-0.83

POSITIVE LOGITS

its

0.98

 self

0.98

 собой

0.97

自身

0.95

self

0.94

 this

0.91

0.90

 خود

0.90

 selves

0.90

 itself

0.88

Activations Density 0.008%

Python special methods and OOP

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. init, str, get, set).

No Comments

No Known Activations

Python special methods and OOP

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. init, str, get, set).

No Comments

No Known Activations

Python special methods and OOP

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. __init__, __str__, __get__, __set__).

No Comments

No Known Activations

Python special methods and OOP

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. __init__, __str__, __get__, __set__).

No Comments

No Known Activations

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. init, str, get, set).

The neuron strongly activates on Python’s “dunder” (double‐underscore) method names (e.g. init, str, get, set).