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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺘ
    -0.08
    ’.
    -0.07
    _si
    -0.07
    $header
    -0.07
     specific
    -0.06
     findBy
    -0.06
     printed
    -0.06
    _lin
    -0.06
     comeback
    -0.06
    ").
    -0.06
    POSITIVE LOGITS
    (Game
    0.07
     of
    0.07
    （平成
    0.07
     leaderboard
    0.06
     диаг
    0.06
     woodworking
    0.06
     Horde
    0.06
    _panel
    0.06
     Chili
    0.06
    писание
    0.06
    Act Density 0.156%

    No Known Activations