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

    Neuronpedia

    INDEX
    Explanations

    win and victory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RAFT
    0.65
    ARKS
    0.64
    ibe
    0.64
    mozilla
    0.64
    raft
    0.61
    IGNED
    0.61
    bedkar
    0.61
     ஒப்பு
    0.60
    ibile
    0.60
    avanja
    0.59
    POSITIVE LOGITS
     win
    4.79
     victory
    4.76
     wins
    4.55
     winning
    4.44
     winner
    4.33
     winners
    4.09
     victories
    4.05
    victory
    4.00
    win
    3.96
    Winning
    3.95
    Act Density 0.207%

    No Known Activations