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

    Neuronpedia

    INDEX
    Explanations

    tactical advantage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    珏
    0.42
     Fédération
    0.41
    feder
    0.40
     feder
    0.39
    尼亚克
    0.39
     FCC
    0.39
     federation
    0.39
     FTIR
    0.38
     lek
    0.38
    ociazione
    0.38
    POSITIVE LOGITS
     defensively
    0.67
     punished
    0.59
    战略
    0.59
     offensively
    0.59
     стратеги
    0.58
     advantage
    0.57
     defensive
    0.57
     avantage
    0.57
     Defensive
    0.57
     punishing
    0.55
    Act Density 0.007%

    No Known Activations