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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ////////////////////////////////////////////////////////////////////////////
    -0.07
     alumni
    -0.07
    Fall
    -0.07
     Neb
    -0.06
    <data
    -0.06
     Lod
    -0.06
     †
    -0.06
    .Rotate
    -0.06
     ↵            ↵
    -0.06
     DataGridView
    -0.06
    POSITIVE LOGITS
    ทร
    0.07
    _verbose
    0.06
    (func
    0.06
    рю
    0.06
     monoc
    0.06
    (bind
    0.06
    odium
    0.06
    ICATION
    0.06
    бас
    0.06
     зер
    0.06
    Act Density 0.006%

    No Known Activations