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

    Neuronpedia

    INDEX
    Explanations

    align

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soru
    -0.07
     거
    -0.06
     nilai
    -0.06
    cps
    -0.06
     sw
    -0.06
    >>)
    -0.06
    _get
    -0.06
    rnd
    -0.06
     investigative
    -0.06
     separators
    -0.06
    POSITIVE LOGITS
     Islands
    0.07
    YOU
    0.07
     الحديث
    0.07
     YOU
    0.07
    ités
    0.06
    Á
    0.06
    Phone
    0.06
    apple
    0.06
     القي
    0.06
    漫画
    0.06
    Act Density 0.003%

    No Known Activations