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

    Neuronpedia

    INDEX
    Explanations

    code attributes and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的大小
    0.41
    footnotesize
    0.38
    كل
    0.34
     yun
    0.34
     spacious
    0.34
     souci
    0.34
     sizes
    0.34
    扩大
    0.34
     CGSize
    0.34
     Kao
    0.33
    POSITIVE LOGITS
     berisi
    0.41
    shapeColor
    0.40
    Probability
    0.39
    durationType
    0.39
    abbanti
    0.39
    ANTED
    0.39
     ಕನ್ನಡ
    0.38
    agnet
    0.38
    ymmetrical
    0.38
    ySpeed
    0.38
    Act Density 0.592%

    No Known Activations