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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    æĿ¥çļĦ
    -0.28
    etable
    -0.27
    å®ŀåľ¨
    -0.27
    tent
    -0.26
    etas
    -0.26
    (indent
    -0.25
    ais
    -0.25
    è²ł
    -0.24
    idf
    -0.24
    éģĵ
    -0.24
    POSITIVE LOGITS
    adays
    0.27
    oteca
    0.26
    Advertis
    0.26
    __.__
    0.25
    ilyn
    0.25
    ocked
    0.24
    æ²Ļåıijä¸Ĭ
    0.24
     Depths
    0.24
     bother
    0.24
    åºĬä¸Ĭ
    0.24
    Act Density 5.594%

    No Known Activations