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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _workers
    -0.07
    _objects
    -0.07
     bang
    -0.06
     Rajasthan
    -0.06
    Measure
    -0.06
    .Initial
    -0.06
    byss
    -0.06
    лас
    -0.06
    _period
    -0.06
    손
    -0.06
    POSITIVE LOGITS
     document
    0.06
     prere
    0.06
    ्म
    0.06
    Н
    0.06
     searcher
    0.06
    (NO
    0.06
     눈을
    0.06
     tả
    0.06
    员
    0.06
     kış
    0.06
    Act Density 0.008%

    No Known Activations