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

    Neuronpedia

    INDEX
    Explanations

    expressions of consent, feedback, and personal opinions

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

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.69
    UrlResolution
    -0.65
     Exactos
    -0.61
    -0.60
    fortawesome
    -0.59
    المناصب
    -0.57
    Lähteet
    -0.56
    Diwedd
    -0.56
    хьтан
    -0.54
    PMailer
    -0.53
    POSITIVE LOGITS
     mergeFrom
    0.46
    kijken
    0.41
    //
    0.38
     aporte
    0.37
     contributing
    0.34
     uitzicht
    0.32
     contribución
    0.32
     persoonlijke
    0.31
     vœux
    0.31
     soldadura
    0.31
    Act Density 0.049%

    No Known Activations