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

    Neuronpedia

    INDEX
    Explanations

    sections or headings denoting abstracts in documents

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

    abstracts and code includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.64
    MLLoader
    -0.62
    ReusableCell
    -0.62
     ویکی‌پدی
    -0.57
    ftagPool
    -0.56
    ChildScrollView
    -0.55
    sizeCache
    -0.55
     gddr
    -0.54
     Italijani
    -0.54
    Marion
    -0.52
    POSITIVE LOGITS
    ABSTRACT
    2.67
     ABSTRACT
    1.49
    RESUMO
    0.69
    STRACT
    0.55
    abstra
    0.55
    SUMMARY
    0.54
    RESUMEN
    0.53
     SUMMARY
    0.52
    abstract
    0.50
     StatefulWidget
    0.46
    Act Density 0.000%

    No Known Activations