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

    Neuronpedia

    INDEX
    Explanations

    Names and nicknames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     argparse
    -0.07
     facilitating
    -0.06
     başar
    -0.06
     bystand
    -0.06
    _PORTS
    -0.06
     seas
    -0.06
    ो
    -0.06
    ика
    -0.06
     bac
    -0.06
     vara
    -0.06
    POSITIVE LOGITS
    悉
    0.07
    任
    0.07
    )=(
    0.06
    vtColor
    0.06
    Every
    0.06
     Wat
    0.06
     dut
    0.06
    ños
    0.06
    InputDialog
    0.06
     Listed
    0.06
    Act Density 0.102%

    No Known Activations