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

    Neuronpedia

    INDEX
    Explanations

    Chinese names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.81
     Weibo
    -0.80
     WeChat
    -0.79
     estekak
    -0.76
     Tianjin
    -0.74
    éphane
    -0.73
    Exeunt
    -0.72
     Italijani
    -0.71
     Beijing
    -0.71
     ſind
    -0.71
    POSITIVE LOGITS
    zi
    0.65
    Z
    0.59
    Fe
    0.57
    '
    0.57
    he
    0.56
    zu
    0.56
    G
    0.56
    ji
    0.54
    ju
    0.54
    ren
    0.54
    Act Density 0.077%

    No Known Activations