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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names and titles in diverse contexts

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

    foreign names and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.90
     HasFactory
    -0.75
    MigrationBuilder
    -0.66
     lenker
    -0.66
    featureID
    -0.65
     ویکی‌پدیا
    -0.64
     nahilalakip
    -0.63
     increí
    -0.62
    पया
    -0.60
    expandindo
    -0.60
    POSITIVE LOGITS
    han
    0.38
    ades
    0.37
    rz
    0.36
    pen
    0.35
    inal
    0.35
    full
    0.35
    les
    0.34
    -
    0.34
     iprot
    0.34
     Full
    0.34
    Act Density 0.078%

    No Known Activations