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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疗
    -0.06
     dáv
    -0.06
     stringent
    -0.06
    Ú
    -0.06
    park
    -0.06
    بح
    -0.06
    通り
    -0.06
    움
    -0.06
    inness
    -0.06
     dall
    -0.06
    POSITIVE LOGITS
    -app
    0.07
    패
    0.07
    (startTime
    0.07
    lds
    0.06
     Σα
    0.06
     комплекс
    0.06
     App
    0.06
     انتخابات
    0.06
     stay
    0.06
     silicon
    0.06
    Act Density 0.011%

    No Known Activations