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

    Neuronpedia

    INDEX
    Explanations

    Unintention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *pow
    -0.07
     broken
    -0.07
    เวลา
    -0.06
     hardly
    -0.06
     пока
    -0.06
     znění
    -0.06
     своих
    -0.06
     Islamabad
    -0.06
     thoroughly
    -0.06
     meals
    -0.06
    POSITIVE LOGITS
     aftermath
    0.07
    获得
    0.07
    934
    0.06
     unintention
    0.06
    onitor
    0.06
     IPO
    0.06
     فرمان
    0.06
     उनक
    0.06
    uitar
    0.06
    alance
    0.06
    Act Density 0.004%

    No Known Activations