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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     봐
    -0.06
    .Ui
    -0.06
    	day
    -0.06
     setPage
    -0.06
     cata
    -0.06
     rush
    -0.06
     acción
    -0.06
     camar
    -0.06
     pair
    -0.06
     fs
    -0.06
    POSITIVE LOGITS
    英国
    0.07
    	up
    0.07
     resisted
    0.07
     hostility
    0.07
    500
    0.06
    �
    0.06
     Huyện
    0.06
    occup
    0.06
    grily
    0.06
    dere
    0.06
    Act Density 0.002%

    No Known Activations