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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    :
    1.11
    .
    1.06
    er
    1.03
    a
    1.02
    ia
    0.93
    am
    0.91
    xture
    0.91
    an
    0.91
    geç
    0.91
     :
    0.90
    POSITIVE LOGITS
     ತನ್ನ
    0.98
    उन्होंने
    0.97
    他们在
    0.95
     وكانت
    0.92
     Gegner
    0.92
     પોતાના
    0.91
    他
    0.91
    📼
    0.91
    他和
    0.89
     그는
    0.87
    Act Density 0.026%

    No Known Activations