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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Points
    -0.08
     Olsen
    -0.07
     Bowen
    -0.07
    ctxt
    -0.07
     Difference
    -0.06
     Cyril
    -0.06
    نج
    -0.06
     coronavirus
    -0.06
    沉
    -0.06
    _registers
    -0.06
    POSITIVE LOGITS
    _REQUIRE
    0.06
    füg
    0.06
    wendung
    0.06
    自动
    0.06
    .SelectedItems
    0.06
     requires
    0.06
    assert
    0.06
    цион
    0.06
     getType
    0.06
    OF
    0.06
    Act Density 0.001%

    No Known Activations