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

    Neuronpedia

    INDEX
    Explanations

    week

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     व्यक्ति
    -0.09
     regard
    -0.08
     jspb
    -0.08
     lesquelles
    -0.08
    оқ
    -0.08
     Elon
    -0.08
    ंजी
    -0.07
     bł
    -0.07
     JAXBElement
    -0.07
     spéc
    -0.07
    POSITIVE LOGITS
    週間
    0.09
    -week
    0.09
    摘要
    0.08
     lunches
    0.08
     brunch
    0.08
     distribu
    0.08
    flower
    0.08
     summer
    0.08
     içinde
    0.07
     comprising
    0.07
    Act Density 0.034%

    No Known Activations