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

    Neuronpedia

    INDEX
    Explanations

    logical AND and OR operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ();}
    0.39
    .},
    0.37
    SEASON
    0.37
    ISPW
    0.36
    地元
    0.36
    ({});
    0.36
    фик
    0.35
    Season
    0.35
    ல்லாம்
    0.34
    രാണ്
    0.34
    POSITIVE LOGITS
     &&
    0.93
    且
    0.73
     thì
    0.72
     ||
    0.67
     then
    0.63
     AND
    0.63
    &&
    0.62
    并且
    0.61
    则
    0.61
     alors
    0.59
    Act Density 0.044%

    No Known Activations