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

    Neuronpedia

    INDEX
    Explanations

    equations of circles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waitress
    -0.09
    .chart
    -0.08
    .Chart
    -0.08
     knitting
    -0.08
     knitted
    -0.08
     Coffee
    -0.08
     CPU
    -0.08
    Cpu
    -0.08
    (chart
    -0.08
     coffee
    -0.08
    POSITIVE LOGITS
    mdir
    0.09
     Unterschiede
    0.09
     स्थल
    0.08
     diferencias
    0.08
     sombras
    0.08
     discrimination
    0.08
     sombra
    0.08
     différences
    0.08
     indawo
    0.08
    eterangan
    0.08
    Act Density 0.057%

    No Known Activations