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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    te
    1.16
    ta
    1.04
    th
    0.86
    ค์
    0.82
    se
    0.80
    gos
    0.80
    Surely
    0.80
    Squares
    0.80
    Feet
    0.79
    t
    0.77
    POSITIVE LOGITS
    ل
    1.29
    ﺭ
    1.00
    ни
    0.94
     with
    0.93
    м
    0.91
     by
    0.89
     い
    0.88
     অধ্যয়ন
    0.88
    لای
    0.88
     त्यासाठी
    0.86
    Act Density 0.355%

    No Known Activations