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

    Neuronpedia

    INDEX
    Explanations

    comparing entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ASK
    0.72
    ASK
    0.71
    ask
    0.67
    asking
    0.65
    Ask
    0.62
    शन
    0.61
     Ask
    0.59
    semer
    0.59
    asko
    0.59
     Rana
    0.59
    POSITIVE LOGITS
     king
    0.67
     force
    0.65
    凤凰
    0.61
     कार्ड
    0.60
     বাব
    0.59
     অভিযোগ
    0.59
    ifen
    0.59
     બંધ
    0.58
     हाइड्रो
    0.57
    үү
    0.56
    Act Density 0.140%

    No Known Activations