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

    Neuronpedia

    INDEX
    Explanations

    type of victory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Comparer
    0.42
    गर्भ
    0.39
    aternion
    0.38
     މަ
    0.38
    有害
    0.37
    چل
    0.37
    rigid
    0.37
    Loved
    0.37
    '][:
    0.36
    を受ける
    0.36
    POSITIVE LOGITS
     victory
    2.92
     victories
    2.53
    victory
    2.52
     victoire
    2.41
     wins
    2.36
     vitória
    2.31
    Victory
    2.30
     win
    2.28
    勝利
    2.28
     Victory
    2.27
    Act Density 0.022%

    No Known Activations