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

    Neuronpedia

    INDEX
    Explanations

    winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Glu
    0.34
     שכ
    0.34
     βοη
    0.33
    Toward
    0.33
    ’
    0.33
     आर्य
    0.33
     hazır
    0.33
    ígenes
    0.32
    沿着
    0.32
     نعمل
    0.32
    POSITIVE LOGITS
     win
    0.66
     battles
    0.58
     victories
    0.57
     victory
    0.55
     championships
    0.55
     승
    0.55
     prizes
    0.51
     decisively
    0.51
     trophies
    0.50
    ชนะ
    0.50
    Act Density 0.014%

    No Known Activations