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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Morrow
    -0.28
    å§ĭ
    -0.28
     Ston
    -0.27
    è´¨éĩıåĴĮ
    -0.27
    æľĹ
    -0.27
    cpy
    -0.26
    UrlParser
    -0.26
    áng
    -0.25
    ocard
    -0.25
    æ¥ŀ
    -0.25
    POSITIVE LOGITS
    è¦ģåİ»
    0.26
    ervations
    0.25
    ç¦Ģ
    0.25
    _________________↵↵
    0.24
    åİŁåĪĻä¸Ĭ
    0.23
     trag
    0.23
    eros
    0.23
     dipped
    0.23
     swallowed
    0.23
    æŃ¤æ¬¡æ´»åĬ¨
    0.23
    Act Density 0.031%

    No Known Activations