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

    Neuronpedia

    INDEX
    Explanations

    emperor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    説明
    -0.08
     انتخابات
    -0.07
     inflicted
    -0.07
     چیز
    -0.07
     z
    -0.07
    制作
    -0.07
     حساب
    -0.07
     Rud
    -0.07
     argv
    -0.06
     öğren
    -0.06
    POSITIVE LOGITS
    PMC
    0.07
    ۲۳
    0.06
    _ADAPTER
    0.06
    /operator
    0.06
    ']
    0.06
    inars
    0.06
     lineHeight
    0.06
    684
    0.06
    ddie
    0.06
    0.06
    Act Density 0.006%

    No Known Activations