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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    arap
    0.46
    0.42
    oling
    0.42
    atlan
    0.42
    rophages
    0.41
    at
    0.41
     स्पून
    0.41
    անկ
    0.40
     Appointment
    0.40
    htub
    0.39
    POSITIVE LOGITS
    ambito
    0.50
    ên
    0.49
    ذهب
    0.48
     travaillé
    0.47
     five
    0.47
    اين
    0.45
     व्यस्त
    0.44
     पाच
    0.44
    ının
    0.43
    ंचे
    0.43
    Act Density 0.001%

    No Known Activations