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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    es
    1.00
    or
    0.86
    м
    0.85
    p
    0.82
    ла
    0.82
    a
    0.81
    in
    0.81
    m
    0.78
    e
    0.77
    an
    0.76
    POSITIVE LOGITS
    ০০
    0.60
     pueda
    0.60
     Epidemi
    0.60
     سيكون
    0.57
     می‌تواند
    0.55
    ૦
    0.54
    ดี
    0.53
    用於
    0.53
     puede
    0.52
    を有する
    0.52
    Act Density 21.026%

    No Known Activations