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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Pro
    -0.08
    Response
    -0.08
    IRM
    -0.08
    _checksum
    -0.08
    Http
    -0.08
    emotion
    -0.08
     соблюдать
    -0.08
    agir
    -0.08
    email
    -0.08
    .response
    -0.07
    POSITIVE LOGITS
     quadratic
    0.10
     pav
    0.10
     দ্ব
    0.09
    quadr
    0.08
     quadrant
    0.08
     Cartesian
    0.08
    �
    0.08
    二维
    0.08
     pencils
    0.08
     overlay
    0.08
    Act Density 0.035%

    No Known Activations