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

    Neuronpedia

    INDEX
    Explanations

    professions and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kojim
    0.33
    which
    0.31
     alph
    0.29
    Likes
    0.29
    MyHomePage
    0.29
     얘가
    0.29
     lightness
    0.29
     NSMutable
    0.28
    忘れ
    0.27
    Maybe
    0.27
    POSITIVE LOGITS
     extraordinaire
    0.58
     who
    0.49
     کرام
    0.46
     extraordin
    0.46
     którzy
    0.45
    দের
    0.44
    들에게
    0.44
     الذين
    0.43
     ktorí
    0.43
     specialising
    0.41
    Act Density 0.095%

    No Known Activations