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

    Neuronpedia

    INDEX
    Explanations

    divine titles and authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இயக்கு
    0.42
    囁
    0.41
    хих
    0.40
    篒
    0.40
     الاخير
    0.39
    コレート
    0.39
    ዃ
    0.38
    褛
    0.38
     آفیسر
    0.38
     الأه
    0.38
    POSITIVE LOGITS
     lord
    0.72
     Lord
    0.72
     Our
    0.66
    Lord
    0.62
    lord
    0.61
     our
    0.60
     almighty
    0.59
     glorious
    0.58
     سيدنا
    0.57
    Our
    0.57
    Act Density 0.013%

    No Known Activations