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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    лы
    0.99
     Еще
    0.99
     часть
    0.98
     पर्याप्त
    0.98
     realizando
    0.98
     Э
    0.97
     подвер
    0.97
    ╽
    0.97
     представитель
    0.96
    Gandhi
    0.96
    POSITIVE LOGITS
     inks
    1.09
     belongings
    0.98
     to
    0.93
    માં
    0.93
     fume
    0.90
     beauty
    0.88
     quarters
    0.88
     pens
    0.86
     wonders
    0.84
     riches
    0.84
    Act Density 0.000%

    No Known Activations