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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    h
    1.44
    ों
    1.00
    0.99
     género
    0.98
     Abelian
    0.96
    ק
    0.95
     tentativo
    0.92
     vehículo
    0.91
     κά
    0.90
    ).
    0.89
    POSITIVE LOGITS
    تهم
    1.30
    ت
    1.28
    서
    1.27
    ब्ल्यू
    1.19
    ナ
    1.19
    고
    1.17
    dı
    1.13
    利
    1.09
    는다
    1.08
    ка
    1.07
    Act Density 0.000%

    No Known Activations