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

    Neuronpedia

    INDEX
    Explanations

    icons and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naming
    0.39
    yaf
    0.38
     create
    0.38
    тию
    0.37
    เหตุ
    0.37
    igheter
    0.37
     طب
    0.36
    givings
    0.36
    urndata
    0.36
     camadas
    0.36
    POSITIVE LOGITS
     icon
    1.56
     symbol
    1.45
     icons
    1.45
    图标
    1.34
     símbolo
    1.34
     symbols
    1.33
     simbolo
    1.29
    アイコン
    1.29
     Icon
    1.28
     simbol
    1.26
    Act Density 0.046%

    No Known Activations