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

    Neuronpedia

    INDEX
    Explanations

    exists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     airport
    -0.07
    -guard
    -0.07
     Flat
    -0.07
     HttpServlet
    -0.06
    macen
    -0.06
     Report
    -0.06
     Polygon
    -0.06
     foll
    -0.06
    rain
    -0.06
     yas
    -0.06
    POSITIVE LOGITS
    .exist
    0.07
     specialized
    0.07
    스를
    0.06
    ships
    0.06
    (isset
    0.06
    .visibility
    0.06
    PDOException
    0.06
    敗
    0.06
    lude
    0.06
    .setMax
    0.06
    Act Density 0.011%

    No Known Activations