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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бед
    -0.07
    #",
    -0.07
     usuario
    -0.06
     Müslüman
    -0.06
    _membership
    -0.06
     Gordon
    -0.06
    _secondary
    -0.06
    -neutral
    -0.06
     sciences
    -0.06
     `${
    -0.06
    POSITIVE LOGITS
    历
    0.06
    IPH
    0.06
     Robin
    0.06
     Cone
    0.06
     dist
    0.06
     그러
    0.06
    ั้
    0.06
     زي
    0.06
    crafted
    0.06
     associate
    0.06
    Act Density 0.000%

    No Known Activations