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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustom
    -0.07
    /auth
    -0.07
    .Keyword
    -0.07
     Them
    -0.06
     hacer
    -0.06
    phem
    -0.06
    aversal
    -0.06
    .Startup
    -0.06
     runnable
    -0.06
    .ends
    -0.06
    POSITIVE LOGITS
     않고
    0.07
    When
    0.07
    кування
    0.07
     кап
    0.06
     Podesta
    0.06
     kỹ
    0.06
     Aspen
    0.06
    ứng
    0.06
     Pixar
    0.06
     nổi
    0.06
    Act Density 0.006%

    No Known Activations