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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    anut
    0.66
     parip
    0.66
     आरमार
    0.66
     odnosu
    0.65
     statutes
    0.64
    }
    0.64
    на
    0.64
    uild
    0.63
    xc
    0.63
     municipality
    0.62
    POSITIVE LOGITS
    𝐰
    0.77
    ここ
    0.74
    首相
    0.73
     ਦਿੱ
    0.71
    我和
    0.71
    你不
    0.69
    転
    0.68
     Lưu
    0.68
     により
    0.68
    這些
    0.67
    Act Density 0.000%

    No Known Activations