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

    Neuronpedia

    INDEX
    Explanations

    nuclear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    變
    -0.07
    μ
    -0.07
     Margin
    -0.07
     Gauss
    -0.07
     renov
    -0.06
    无线
    -0.06
    已经超过
    -0.06
     hann
    -0.06
     medieval
    -0.06
     OB
    -0.06
    POSITIVE LOGITS
    key
    0.07
     Đặc
    0.07
     EntityState
    0.07
    筢
    0.07
     clr
    0.07
     :\
    0.06
    ataires
    0.06
    [loc
    0.06
    [W
    0.06
    ゎ
    0.06
    Act Density 0.009%

    No Known Activations