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

    Neuronpedia

    INDEX
    Explanations

    coordinate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anfitrión
    -1.02
    ꒥
    -0.90
     gloomy
    -0.88
    bidities
    -0.87
     olmayan
    -0.86
    rowave
    -0.85
    Anyway
    -0.83
     adatta
    -0.81
    usure
    -0.81
     daunting
    -0.81
    POSITIVE LOGITS
    axes
    0.95
    轴
    0.92
    ?',
    0.91
     lagar
    0.91
     mesta
    0.91
     Axes
    0.90
     fú
    0.90
    Способ
    0.89
    ：</
    0.88
     */,
    0.88
    Act Density 0.013%

    No Known Activations