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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tenían
    0.90
     зміни
    0.85
    e
    0.85
    punyai
    0.84
     jugando
    0.82
     која
    0.80
    改变
    0.80
    łasz
    0.80
    ک
    0.77
     своего
    0.77
    POSITIVE LOGITS
     am
    0.64
    ξύ
    0.61
     way
    0.61
    imet
    0.61
    ंबा
    0.60
     Thi
    0.59
     massaging
    0.59
     drivers
    0.58
    лом
    0.58
    ί
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.