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

    Neuronpedia

    INDEX
    Explanations

    sword and swordsmanship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.92
    지
    0.83
    ek
    0.83
    ли
    0.80
    it
    0.77
    ல்
    0.76
    al
    0.73
    اب
    0.70
    us
    0.69
    的具体
    0.69
    POSITIVE LOGITS
     sword
    0.73
    劍
    0.72
    Sword
    0.70
    ות
    0.66
     Sword
    0.65
     quente
    0.64
    ફેદ
    0.63
    あなたが
    0.63
     elenc
    0.62
     swords
    0.59
    Act Density 0.003%

    No Known Activations