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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kể
    0.82
    nosed
    0.82
     talaga
    0.82
     kính
    0.81
     cuánto
    0.81
     mẽ
    0.81
    beweg
    0.80
     Reagan
    0.80
    вался
    0.80
    iebel
    0.80
    POSITIVE LOGITS
    т
    0.77
    Bro
    0.73
    خ
    0.73
     فاط
    0.73
    ج
    0.72
    د
    0.71
     Би
    0.69
    яр
    0.69
    για
    0.69
    (\
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.