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

    Neuronpedia

    INDEX
    Explanations

    prediction and explanation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (transaction
    -0.07
    :Register
    -0.07
     talented
    -0.07
     slave
    -0.07
     ')[
    -0.06
    ادث
    -0.06
     nächsten
    -0.06
    stitute
    -0.06
    라는
    -0.06
     инструк
    -0.06
    POSITIVE LOGITS
     Giới
    0.06
     guarding
    0.06
     HttpServletResponse
    0.06
    .drawText
    0.06
    Verify
    0.06
    AreaView
    0.06
     глиб
    0.06
    ़त
    0.06
     voted
    0.06
    کات
    0.06
    Act Density 0.070%

    No Known Activations