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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    is
    0.86
    スナー
    0.75
    li
    0.73
    Royal
    0.73
    ar
    0.70
    il
    0.70
    Sz
    0.69
    ler
    0.68
    é
    0.68
    lar
    0.68
    POSITIVE LOGITS
    ческую
    0.87
     повы
    0.84
     профе
    0.82
    ното
    0.80
    йт
    0.80
    穸
    0.80
    ственной
    0.79
    ческому
    0.77
    про
    0.76
     умень
    0.76
    Act Density 0.001%

    No Known Activations