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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    是
    0.70
    人
    0.66
    帶
    0.65
    টা
    0.64
    乘以
    0.64
    外套
    0.64
     —
    0.63
    堆
    0.63
    衹
    0.63
     REI
    0.63
    POSITIVE LOGITS
    ambique
    0.80
    ل
    0.80
     kıl
    0.78
    inson
    0.77
     סי
    0.74
     สาว
    0.72
     Joomla
    0.71
     Thunderbird
    0.71
     kembali
    0.70
     Yogyakarta
    0.69
    Act Density 0.007%

    No Known Activations