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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     모르
    -0.06
    amac
    -0.06
    ILogger
    -0.06
    رود
    -0.06
    ่อไป
    -0.06
     när
    -0.06
    ماری
    -0.06
    хов
    -0.06
     جوان
    -0.06
     долж
    -0.06
    POSITIVE LOGITS
    Revision
    0.07
    %'
    0.06
    ُن
    0.06
    _al
    0.06
    db
    0.06
     stove
    0.06
    kos
    0.06
     Hayes
    0.06
    yb
    0.06
    複
    0.06
    Act Density 0.008%

    No Known Activations