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

    Neuronpedia

    INDEX
    Explanations

    numeric values or formatting in technical contexts

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.77
     surla
    -0.73
    ſchaft
    -0.70
    enablog
    -0.70
    ロウィン
    -0.69
     كومونز
    -0.66
     deſſen
    -0.65
    ſehen
    -0.65
     Signalez
    -0.64
    orianCalendar
    -0.63
    POSITIVE LOGITS
     âmes
    0.38
     inspección
    0.36
     sauvages
    0.35
     Juifs
    0.34
     récents
    0.33
     neumáticos
    0.32
     actuels
    0.31
     vertrouwen
    0.31
     estabilidad
    0.30
     normaux
    0.30
    Act Density 0.001%

    No Known Activations