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

    Neuronpedia

    INDEX
    Explanations

    TED

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    */↵↵↵
    -0.07
    CRT
    -0.07
    ynn
    -0.07
    Aspect
    -0.07
    ꜥ
    -0.07
    red
    -0.07
    Rua
    -0.07
    ﷻ
    -0.07
    Arc
    -0.07
    렙
    -0.07
    POSITIVE LOGITS
     ordained
    0.07
    .pagination
    0.07
    习惯
    0.07
    .DEFINE
    0.07
     Hon
    0.07
    Https
    0.07
     대통령
    0.07
    _te
    0.06
    /mainwindow
    0.06
    .EventHandler
    0.06
    Act Density 0.002%

    No Known Activations