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

    Neuronpedia

    INDEX
    Explanations

    interface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æīİ
    -0.30
    åĮĸ
    -0.29
    æī¹
    -0.28
    åĢ¾
    -0.28
     Champ
    -0.28
    ç³»
    -0.28
    .Itoa
    -0.26
    æŁ´
    -0.26
    INGS
    -0.26
    rewrite
    -0.26
    POSITIVE LOGITS
    åįıä¼ļä¼ļåijĺ
    0.31
    çļĦä¿¡ä»»
    0.27
    éĢĤåIJĪèĩªå·±
    0.27
    身躯
    0.27
    æīĭèħķ
    0.27
    çļĦè®¤çŁ¥
    0.27
    åĮį
    0.26
    润æ»ijæ²¹
    0.26
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.26
    çĶ·åıĭ
    0.26
    Act Density 0.089%

    No Known Activations