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

    Neuronpedia

    INDEX
    Explanations

    defining code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cavité
    0.46
     ecológica
    0.44
    🏞
    0.44
     ㅎ
    0.43
     灬
    0.43
    入場
    0.43
     जुटा
    0.42
    ಾಯಿ
    0.41
    🚛
    0.41
     канторы
    0.41
    POSITIVE LOGITS
    newcommand
    0.71
    define
    0.68
    def
    0.65
     define
    0.62
     Define
    0.59
    Define
    0.56
     def
    0.55
     defines
    0.53
     redefine
    0.53
     defined
    0.52
    Act Density 0.005%

    No Known Activations