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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dealings
    -0.07
    گانی
    -0.07
    PR
    -0.07
     alternating
    -0.06
    MISSION
    -0.06
     stupidity
    -0.06
     ''),↵
    -0.06
    Into
    -0.06
    ifen
    -0.06
    866
    -0.06
    POSITIVE LOGITS
    شو
    0.06
    ヤ
    0.06
     sanctions
    0.06
     digit
    0.06
    ichert
    0.06
    _verbose
    0.06
     моб
    0.06
     Sellers
    0.06
    _unicode
    0.06
    >Main
    0.06
    Act Density 0.000%

    No Known Activations