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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    坐下
    -0.08
    tsy
    -0.07
    VOID
    -0.07
    扭转
    -0.07
     enact
    -0.07
     książ
    -0.07
    (px
    -0.07
    .ok
    -0.07
     clumsy
    -0.07
    rink
    -0.06
    POSITIVE LOGITS
     Kurdistan
    0.08
     Library
    0.08
     analyzer
    0.07
    使用权
    0.07
    学家
    0.07
    icast
    0.07
    发电机
    0.07
     Castro
    0.07
    حوا
    0.07
    HTTP
    0.07
    Act Density 0.001%

    No Known Activations