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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .obj
    -0.07
    掉
    -0.06
    uação
    -0.06
     wissen
    -0.06
    errupted
    -0.06
     resisted
    -0.06
     зада
    -0.06
    _Interface
    -0.06
    自分
    -0.06
     miracle
    -0.06
    POSITIVE LOGITS
     Ürün
    0.07
    ograms
    0.07
     Bed
    0.07
     hafif
    0.06
     alarak
    0.06
    ıt
    0.06
    igrations
    0.06
     çat
    0.06
     også
    0.06
     вне
    0.06
    Act Density 0.065%

    No Known Activations