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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     constitución
    0.53
     patriotism
    0.49
     мра
    0.48
    mor
    0.48
    ກະ
    0.47
     patriots
    0.46
     Ио
    0.46
    <unused236>
    0.45
    ຍ
    0.45
     стоит
    0.44
    POSITIVE LOGITS
    خت
    0.48
    انج
    0.47
    بي
    0.43
    ب
    0.43
     Mena
    0.42
    ي
    0.42
     فيها
    0.41
     ن
    0.40
    erts
    0.40
    erede
    0.40
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.