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

    Neuronpedia

    INDEX
    Explanations

    crime victimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     புரிந்து
    0.50
    dometer
    0.43
    де
    0.43
     अथवा
    0.40
    드를
    0.40
     шаблон
    0.40
     disgust
    0.39
    гийн
    0.39
     ಸೂಚ
    0.39
     regresa
    0.39
    POSITIVE LOGITS
     belangrijk
    0.41
     createState
    0.40
     U
    0.39
     esquina
    0.39
    ！)
    0.39
    an
    0.39
    "-
    0.39
    innie
    0.38
     बाएं
    0.38
     justamente
    0.38
    Act Density 0.007%

    No Known Activations