INDEX

Explanations

__ followed by keywords

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

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. init, get).

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

 morbidity

-0.76

Nt

-0.75

 baker

-0.75

Kid

-0.74

loth

-0.71

PIG

-0.71

 finder

-0.71

okan

-0.71

KID

-0.70

 metallurgy

-0.69

POSITIVE LOGITS

__(

0.86

__::

0.79

__.

0.75

Recher

0.74

__,

0.73

__:

0.73

 통해

0.72

%,

0.71

 хотите

0.70

吼

0.68

Activations Density 0.047%

__ followed by keywords

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. init, get).

No Comments

No Known Activations

__ followed by keywords

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. init, get).

No Comments

No Known Activations

__ followed by keywords

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. __init__, __get__).

No Comments

No Known Activations

__ followed by keywords

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. __init__, __get__).

No Comments

No Known Activations

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. init, get).

The neuron consistently fires on code-like tokens—especially those containing digits or underscores—such as numeric literals, macro/constant names, and “dunder” identifiers (e.g. init, get).