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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uur
    0.79
    ↵
    0.77
    怎么办
    0.71
    荣耀
    0.66
    ia
    0.64
    ij
    0.64
    xbet
    0.64
    urang
    0.64
    yship
    0.63
    ી
    0.62
    POSITIVE LOGITS
    та
    0.97
     tensão
    0.96
     바
    0.94
     bá
    0.93
    玴
    0.93
     спа
    0.91
     сты
    0.90
     ലഭ
    0.90
     длин
    0.90
     फार
    0.88
    Act Density 0.000%

    No Known Activations