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

    Neuronpedia

    INDEX
    Explanations

    Code and descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.78
    gameserver
    -0.72
    出版年
    -0.71
     للمعارف
    -0.69
     الرياضيه
    -0.68
    MessageOf
    -0.67
     Мексичка
    -0.65
    PMailer
    -0.62
    RectangleBorder
    -0.61
     Autorizaciones
    -0.59
    POSITIVE LOGITS
     consultato
    0.52
    lue
    0.51
     essentially
    0.50
    uscular
    0.48
    essentially
    0.48
     basically
    0.48
    يمق
    0.47
    Normdaten
    0.46
     ur
    0.46
     šť
    0.46
    Act Density 0.000%

    No Known Activations