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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ंबू
    0.81
    o
    0.72
     crown
    0.71
     latest
    0.70
     biggest
    0.69
    乐
    0.68
     stop
    0.68
    秘书
    0.68
    毒
    0.67
    الم
    0.66
    POSITIVE LOGITS
     Также
    1.05
     Поскольку
    0.98
     Мы
    0.98
     Бы
    0.96
     Стра
    0.96
    ность
    0.95
     TRANSPORTURI
    0.93
     Использу
    0.90
     происходит
    0.89
     соблю
    0.88
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.