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

    Neuronpedia

    INDEX
    Explanations

    performs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cunt
    -0.06
    िक
    -0.06
     Graphic
    -0.06
    ывая
    -0.06
     saturated
    -0.06
     uptime
    -0.06
     слыш
    -0.06
    -metadata
    -0.06
    _scripts
    -0.06
     зуб
    -0.06
    POSITIVE LOGITS
     struck
    0.07
    ไฟล
    0.06
    FromDate
    0.06
    manda
    0.06
     ilgi
    0.06
    ��이지
    0.06
    аліст
    0.06
    غن
    0.06
     HT
    0.06
    Luckily
    0.06
    Act Density 0.000%

    No Known Activations