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

    Neuronpedia

    INDEX
    Explanations

    Jaguar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dict
    -0.06
     레벨
    -0.06
    окумент
    -0.06
     bildir
    -0.06
    	date
    -0.06
     hodnot
    -0.06
    ."'
    -0.06
    -0.06
     ти
    -0.06
     dinero
    -0.06
    POSITIVE LOGITS
    襲
    0.07
     Sy
    0.07
     Taiwanese
    0.06
    supported
    0.06
    wegian
    0.06
    volt
    0.06
    Card
    0.06
     revelation
    0.06
     регули
    0.06
    ươi
    0.06
    Act Density 0.091%

    No Known Activations