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

    Neuronpedia

    INDEX
    Explanations

    declination/ascension

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipl
    -0.28
    æ°ijèIJ¥
    -0.27
    æIJı
    -0.27
    ipt
    -0.26
    éĹ°
    -0.26
    åŃº
    -0.25
    ertz
    -0.25
     hã
    -0.25
    éħįéŁ³
    -0.25
    æĸ¥
    -0.25
    POSITIVE LOGITS
     artikel
    0.28
    amac
    0.28
    -piece
    0.28
    ottes
    0.26
     Success
    0.25
    agos
    0.25
    çĭIJ
    0.25
    æµģ转
    0.25
    æıIJåIJį
    0.24
     Hack
    0.24
    Act Density 0.002%

    No Known Activations