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

    Neuronpedia

    INDEX
    Explanations

    numbers in the teens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worldwide
    -0.07
     하면
    -0.07
     Naked
    -0.07
    只能
    -0.06
    hum
    -0.06
     straightforward
    -0.06
    (std
    -0.06
     twig
    -0.06
    -Col
    -0.06
     fores
    -0.06
    POSITIVE LOGITS
     robes
    0.07
    serter
    0.06
    ısına
    0.06
    allo
    0.06
    artial
    0.06
    섭
    0.06
    али
    0.06
    ивать
    0.06
    omial
    0.06
    executable
    0.06
    Act Density 0.000%

    No Known Activations