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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     انج
    -0.07
    (Editor
    -0.07
     inviting
    -0.07
     rapide
    -0.06
     फर
    -0.06
     छ
    -0.06
    .widgets
    -0.06
     BlockPos
    -0.06
     PointF
    -0.06
     Μαρ
    -0.06
    POSITIVE LOGITS
    debug
    0.07
     tcp
    0.06
    cott
    0.06
     -*
    0.06
     Airbnb
    0.06
    ไป
    0.06
     üzerine
    0.06
    quete
    0.06
    279
    0.06
     regardless
    0.06
    Act Density 0.002%

    No Known Activations