Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of code or programming-related segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical and code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    styleType
    -0.87
    AnimationsModule
    -0.80
    <bos>
    -0.78
     ब्रेकडाउन
    -0.72
    aarrggbb
    -0.71
     Chriftian
    -0.66
     Photocase
    -0.65
    TypedDataSet
    -0.65
     ویکی‌پدی
    -0.65
    دانشنامهٔ
    -0.65
    POSITIVE LOGITS
    </code>
    0.77
    \]
    0.60
    </u>
    0.57
    </sub>
    0.56
    </em>
    0.54
    </i>
    0.53
    }}$
    0.52
    }`
    0.50
    }\]
    0.48
    )}$
    0.47
    Act Density 0.111%

    No Known Activations