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

    Neuronpedia

    INDEX
    Explanations

    jokes and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philosophy
    -0.07
    XD
    -0.06
     illumination
    -0.06
     Sidd
    -0.06
    .init
    -0.06
    Intermediate
    -0.06
    _LAYOUT
    -0.06
     folding
    -0.06
    ULD
    -0.06
     أعلام
    -0.06
    POSITIVE LOGITS
     Phar
    0.06
    organ
    0.06
    Crow
    0.06
    -touch
    0.06
     nurse
    0.06
     cowork
    0.06
     cog
    0.06
     Clara
    0.06
     engineer
    0.06
     elkaar
    0.06
    Act Density 0.003%

    No Known Activations