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

    Neuronpedia

    INDEX
    Explanations

    computing or scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trade
    0.58
     Trade
    0.55
    Trade
    0.52
     traded
    0.50
    trade
    0.47
    traded
    0.46
     trading
    0.43
     tradeoffs
    0.43
     trades
    0.43
    貿易
    0.43
    POSITIVE LOGITS
    idding
    0.39
     *}$
    0.37
     [{"
    0.35
    Ắ
    0.35
    жка
    0.35
    رشف
    0.35
    ąż
    0.35
    ว้
    0.35
    satellite
    0.34
     الکتر
    0.34
    Act Density 0.000%

    No Known Activations