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

    Neuronpedia

    INDEX
    Explanations

    voluntary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    è¶Ĭå¤ļ
    -0.27
     al
    -0.26
    æ³°
    -0.25
     Sou
    -0.24
     in
    -0.24
    èĮ¹
    -0.24
     Sur
    -0.24
    æīĢæıIJä¾Ľ
    -0.24
    æĻº
    -0.24
    éĺ²æ°´
    -0.23
    POSITIVE LOGITS
    agas
    0.30
    èĢĮåĩº
    0.30
    åĴĮ个人
    0.29
    该åħ¬åı¸
    0.27
    eut
    0.25
    udy
    0.25
    extends
    0.25
    sty
    0.24
     xsi
    0.24
     suck
    0.24
    Act Density 0.010%

    No Known Activations