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

    Neuronpedia

    INDEX
    Explanations

    generals and military leaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    corruption
    0.62
    resonance
    0.61
    roar
    0.58
    p
    0.58
    𝑜
    0.57
     провести
    0.56
    чками
    0.56
    ro
    0.55
    ান
    0.55
    লোকের
    0.55
    POSITIVE LOGITS
     جنگ
    0.58
     الجيش
    0.51
    '],$
    0.50
    ف
    0.50
     اسٹ
    0.50
     armies
    0.49
    起床
    0.49
     жаңы
    0.49
     perang
    0.49
     کرمان
    0.48
    Act Density 0.010%

    No Known Activations