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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     المنتخب
    0.41
     思う
    0.41
    在于
    0.41
    itado
    0.41
    検討
    0.40
    unregister
    0.40
    urel
    0.39
    려는
    0.39
    0.39
    세기
    0.39
    POSITIVE LOGITS
    πε
    0.41
    Dix
    0.41
    逆
    0.40
     positiva
    0.39
    Positive
    0.38
     চতু
    0.38
     casser
    0.38
    పో
    0.38
     turbines
    0.38
     positif
    0.37
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.