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

    Neuronpedia

    INDEX
    Explanations

    winning or victory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     불편
    0.81
     පරි
    0.74
     بررسی
    0.74
     लष्
    0.73
    륨
    0.73
    ેર
    0.73
    Kontakt
    0.72
     접근
    0.72
     इंजेक्शन
    0.71
     处理
    0.70
    POSITIVE LOGITS
     winning
    3.31
     wins
    2.98
     win
    2.96
    winning
    2.82
    Winning
    2.79
     Winning
    2.77
    win
    2.37
     Wins
    2.35
     victory
    2.35
    wins
    2.32
    Act Density 0.395%

    No Known Activations