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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    henko
    -0.89
    ativity
    -0.73
    olo
    -0.71
    MpServer
    -0.68
    azine
    -0.66
     MP
    -0.64
    imov
    -0.62
    ":["
    -0.62
    izable
    -0.62
    boxing
    -0.60
    POSITIVE LOGITS
    STEP
    0.77
    è¦
    0.76
    è¯
    0.76
    ãĥĨ
    0.73
    é¾
    0.72
    artment
    0.68
    ãĥ³ãĤ¸
    0.67
    yang
    0.66
    ãĥ¯
    0.66
    æĸ¹
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.