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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hưởng
    -0.09
    霁
    -0.08
    หมอ
    -0.07
    中国移动
    -0.07
     ImageButton
    -0.07
     Roland
    -0.07
    iterate
    -0.07
    忤
    -0.07
    О
    -0.07
    鲧
    -0.07
    POSITIVE LOGITS
    בדיקת
    0.08
    :min
    0.07
     ś
    0.07
    isser
    0.07
    _pr
    0.07
     didSelect
    0.07
    égor
    0.06
     titled
    0.06
    说实
    0.06
    ?key
    0.06
    Act Density 0.035%

    No Known Activations