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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     prácticamente
    0.54
     praticamente
    0.52
    聃
    0.51
    ट्स
    0.49
     dihar
    0.49
    σον
    0.49
     direitos
    0.48
     laranja
    0.47
    ницы
    0.46
     MINISTER
    0.46
    POSITIVE LOGITS
    nard
    0.45
    ample
    0.43
    لعاب
    0.43
    inflate
    0.43
    ن
    0.42
    nig
    0.42
    affiliated
    0.42
    }}(\
    0.42
    construction
    0.42
    ())))
    0.41
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.