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

    Neuronpedia

    INDEX
    Explanations

    references to female characters and personal relationships

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

    she, her, mother, grandmother

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     King
    -0.43
     Hahn
    -0.39
     Crown
    -0.38
     Rainbow
    -0.36
    copyTo
    -0.36
     B
    -0.35
    kolle
    -0.35
     Sel
    -0.35
     Pav
    -0.34
     Lot
    -0.34
    POSITIVE LOGITS
     kasarigan
    0.69
     незавершена
    0.65
    Personensuche
    0.63
     الرياضيه
    0.60
    RTEX
    0.58
    AddHtmlAttribute
    0.58
     Numerade
    0.58
     IBOutlet
    0.55
    TypedDataSet
    0.54
     pinulongan
    0.54
    Act Density 0.063%

    No Known Activations