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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     iris
    -0.07
     Laurent
    -0.07
     dalle
    -0.07
     thé
    -0.06
     Clothes
    -0.06
    (calendar
    -0.06
     Restaurant
    -0.06
     Lewis
    -0.06
     factories
    -0.06
     spatial
    -0.06
    POSITIVE LOGITS
    مدة
    0.07
    дом
    0.07
    ihan
    0.06
    第
    0.06
    ->{'
    0.06
    .webkit
    0.06
    ylim
    0.06
    ########################################
    0.06
     Kostenlos
    0.06
    Ltd
    0.06
    Act Density 0.024%

    No Known Activations