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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    爀
    0.80
    tur
    0.74
     gitar
    0.73
    tail
    0.72
    tolerance
    0.70
    ින්
    0.70
    iktar
    0.69
    toler
    0.68
    sampling
    0.67
    smoke
    0.67
    POSITIVE LOGITS
     françaises
    0.77
    ciones
    0.73
     côtés
    0.70
     compét
    0.70
     ฝ
    0.70
     Numerous
    0.69
     Pero
    0.69
     promul
    0.68
     এশিয়ার
    0.68
    et
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.