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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ä»ĬæĹ¥
    -0.26
    éĿĴ
    -0.25
    ä¸įçĶ¨
    -0.25
    论è¯ģ
    -0.25
    éĺµ
    -0.25
    JS
    -0.25
    赤
    -0.25
    (gl
    -0.25
     lĩnh
    -0.24
    OfString
    -0.24
    POSITIVE LOGITS
    æĶ¾æĿ¾
    0.26
    éĤ£ä»½
    0.26
    被æīĵ
    0.26
     Grow
    0.25
    -grow
    0.25
    çļĦæĪIJéķ¿
    0.24
    åľ°åĮºçļĦ
    0.24
    uron
    0.24
    åħ¨ä½ĵåijĺå·¥
    0.24
    åľ¨æķ´ä¸ª
    0.24
    Act Density 0.004%

    No Known Activations