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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ثلاث
    -0.07
     inadequate
    -0.07
    www
    -0.07
     😉↵↵
    -0.07
     australia
    -0.07
    //=
    -0.07
    日本の
    -0.06
     بي
    -0.06
     japan
    -0.06
    菠
    -0.06
    POSITIVE LOGITS
     pots
    0.07
    لق
    0.07
    (plugin
    0.07
    хот
    0.07
    免责声明
    0.07
    ignKey
    0.06
    zens
    0.06
    провод
    0.06
     migrations
    0.06
    ⏱
    0.06
    Act Density 0.021%

    No Known Activations