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

    Neuronpedia

    INDEX
    Explanations

    Chemical formulas and identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Associates
    -0.07
    न
    -0.07
     Prest
    -0.06
    /C
    -0.06
     bitterly
    -0.06
    ccb
    -0.06
     zwei
    -0.06
     Wyn
    -0.06
    แพ
    -0.06
    _FOR
    -0.06
    POSITIVE LOGITS
    иться
    0.07
    σμα
    0.07
     деревян
    0.07
     sağlıklı
    0.07
     menggunakan
    0.06
     "),↵
    0.06
     `,↵
    0.06
     Daemon
    0.06
    WIDTH
    0.06
    ":"","
    0.06
    Act Density 0.002%

    No Known Activations