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

    Neuronpedia

    INDEX
    Explanations

    gym

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transl
    -0.07
    cá
    -0.07
    /high
    -0.07
    River
    -0.07
     data
    -0.07
    ��
    -0.07
    主板
    -0.07
    将成为
    -0.07
     Moy
    -0.07
    頻
    -0.07
    POSITIVE LOGITS
     kiş
    0.08
    眼
    0.07
    ܨ
    0.07
     liking
    0.07
     gym
    0.07
    灵感
    0.07
    "Well
    0.07
    하세요
    0.07
    igsaw
    0.07
    YM
    0.07
    Act Density 0.003%

    No Known Activations