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

    Neuronpedia

    INDEX
    Explanations

    references to user comments and interactions in a conversational context

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

    referring to your statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Federal
    -0.41
     émer
    -0.35
     féd
    -0.32
    ientôt
    -0.32
     federal
    -0.32
     digital
    -0.30
     sélectionnez
    -0.30
    没办法
    -0.29
     physical
    -0.29
    Federal
    -0.29
    POSITIVE LOGITS
    Personendaten
    0.80
     HasFactory
    0.67
    findpost
    0.66
     فريبيس
    0.64
     nakalista
    0.64
    usermodel
    0.61
     Exacts
    0.60
     estekak
    0.56
    Espèce
    0.56
    yourself
    0.54
    Act Density 0.049%

    No Known Activations