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

    Neuronpedia

    INDEX
    Explanations

    database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    积
    -0.36
    涡
    -0.28
    WARE
    -0.28
    ç©į
    -0.27
    hold
    -0.27
    деÑĢж
    -0.27
    toc
    -0.26
     Experimental
    -0.26
     seeded
    -0.26
    ç³Ļ
    -0.25
    POSITIVE LOGITS
     Pluto
    0.30
     prol
    0.28
     Auss
    0.27
    æģŃåĸľ
    0.26
     Pruitt
    0.26
    ç½ijç«Ļåľ°åĽ¾
    0.26
    é¼¾
    0.26
    å¤Ħå¤Ħéķ¿
    0.26
     sno
    0.25
    èĢģåħµ
    0.25
    Act Density 0.058%

    No Known Activations