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

    Neuronpedia

    INDEX
    Explanations

    css properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дослід
    0.84
     Accord
    0.79
     लॉन्
    0.76
     ड्रॉ
    0.75
     Titel
    0.74
     Themen
    0.74
    Title
    0.73
    ساعدة
    0.73
    0.72
     chancellor
    0.72
    POSITIVE LOGITS
    display
    2.01
     display
    1.92
    Display
    1.58
     Display
    1.56
    margin
    1.48
     displays
    1.46
     /*
    1.41
    ディスプレイ
    1.40
    DISPLAY
    1.36
     DISPLAY
    1.34
    Act Density 0.229%

    No Known Activations