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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    浥
    0.97
    玧
    0.91
     регі
    0.90
    Посилання
    0.90
    ный
    0.89
     світу
    0.89
    죠
    0.88
     істо
    0.87
    ті
    0.85
     hiện
    0.84
    POSITIVE LOGITS
     “
    0.75
     chef
    0.70
    ﹌
    0.69
    ق
    0.68
    m
    0.64
    عد
    0.63
     phrasing
    0.63
    شان
    0.62
     Dated
    0.61
    ف
    0.61
    Act Density 0.000%

    No Known Activations