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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Label
    -0.07
     SEC
    -0.07
    َف
    -0.07
    -buffer
    -0.07
     finished
    -0.07
     testcase
    -0.06
    {
↵
↵
    -0.06
     biology
    -0.06
     UM
    -0.06
     slog
    -0.06
    POSITIVE LOGITS
    [date
    0.07
     skills
    0.06
    moth
    0.06
    morgan
    0.06
    ических
    0.06
    母亲
    0.06
    ando
    0.06
    <Category
    0.06
    播放
    0.06
    İTESİ
    0.06
    Act Density 0.002%

    No Known Activations