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

    Neuronpedia

    INDEX
    Explanations

    um

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    •
    -0.07
     tailor
    -0.06
     Secondary
    -0.06
    snap
    -0.06
    nee
    -0.06
     wym
    -0.06
     unpl
    -0.06
    (factory
    -0.06
     forg
    -0.06
     cartridges
    -0.06
    POSITIVE LOGITS
     DataTable
    0.18
    DataTable
    0.18
    abella
    0.11
    dataTable
    0.11
    quist
    0.09
     Gingrich
    0.09
    uč
    0.08
    _bug
    0.08
     dataTable
    0.08
    .DataTable
    0.08
    Act Density 0.003%

    No Known Activations