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

    Neuronpedia

    INDEX
    Explanations

    military operations and psychology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dır
    0.58
    p
    0.52
    ي
    0.52
    i
    0.51
    d
    0.48
    म
    0.46
    권
    0.45
    ку
    0.45
     चौथ
    0.44
     Лондон
    0.44
    POSITIVE LOGITS
     military
    0.56
     군
    0.51
     militaire
    0.48
     army
    0.47
     infantry
    0.47
     an
    0.42
     Army
    0.40
    ing
    0.40
    Army
    0.40
    军
    0.40
    Act Density 0.023%

    No Known Activations