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

    Neuronpedia

    INDEX
    Explanations

    medicine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NE
    -0.30
    /exec
    -0.28
    ne
    -0.28
    neh
    -0.27
     NE
    -0.27
    §è¡Į
    -0.27
    çĭ¬ç«ĭèij£äºĭ
    -0.27
    äºĴ
    -0.26
    èĩªå¾ĭ
    -0.26
    AGER
    -0.25
    POSITIVE LOGITS
     Hind
    0.25
    åľ¨åŃ¦æł¡
    0.25
    ulls
    0.24
    itations
    0.24
    éĿ¢å¯¹
    0.23
    询
    0.23
     Fool
    0.23
    acco
    0.23
    为ä¼ģä¸ļ
    0.23
     Koch
    0.23
    Act Density 0.002%

    No Known Activations