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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ار
    0.83
    ام
    0.77
    さて
    0.74
     floors
    0.71
    ለያዩ
    0.69
    摂
    0.67
     Queste
    0.67
    bbero
    0.65
    いわ
    0.65
     bou
    0.63
    POSITIVE LOGITS
    manı
    1.04
    ský
    0.91
     dotyczą
    0.90
    ონის
    0.90
    ourcen
    0.88
    man
    0.86
    Ი
    0.85
    Ა
    0.84
    thebetterindia
    0.83
    side
    0.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.