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

    Neuronpedia

    INDEX
    Explanations

    overcoming difficulties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    assign
    -0.28
    (assign
    -0.27
    Assign
    -0.26
    .assign
    -0.26
     judging
    -0.26
    _assigned
    -0.26
     ama
    -0.26
    åı£æ°´
    -0.26
    缮
    -0.25
    epad
    -0.25
    POSITIVE LOGITS
    umbs
    0.27
    ä¸ĩè¾Ĩ
    0.25
     equiv
    0.25
    对æĪijæĿ¥è¯´
    0.25
    æīĭæĮĩ
    0.25
    DownList
    0.24
    幡
    0.24
    æıIJåĩºçļĦ
    0.24
    warts
    0.23
    /extensions
    0.23
    Act Density 0.014%

    No Known Activations