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

    Neuronpedia

    INDEX
    Explanations

    discussing American challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ;-)
    0.62
     :-)
    0.59
    :-)
    0.57
     nasty
    0.57
     😘
    0.57
     fait
    0.56
    いろいろ
    0.54
     IMHO
    0.53
    Notwithstanding
    0.52
     naughty
    0.52
    POSITIVE LOGITS
     preventative
    0.48
    LogIn
    0.47
     solely
    0.46
    适用于
    0.45
    无数
    0.44
    Necessary
    0.43
    教育
    0.43
     Necessary
    0.43
    Raleway
    0.43
    Accessibility
    0.43
    Act Density 0.002%

    No Known Activations