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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ب
    1.98
    요
    1.92
     delusion
    1.84
    мо
    1.83
    لل
    1.82
    슨
    1.80
    が生
    1.79
     defrost
    1.77
     defer
    1.72
     bluff
    1.68
    POSITIVE LOGITS
     étrang
    1.99
     numele
    1.97
    intégr
    1.92
     وبعد
    1.91
    i
    1.91
    imilar
    1.90
    Puedes
    1.87
    みました
    1.84
     égaux
    1.82
    ো
    1.82
    Act Density 0.349%

    No Known Activations