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

    Neuronpedia

    INDEX
    Explanations

    publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OUT
    -0.07
    -up
    -0.07
     dto
    -0.07
    _wallet
    -0.06
    ó
    -0.06
    971
    -0.06
     fitting
    -0.06
    (KEY
    -0.06
     CL
    -0.06
    03
    -0.06
    POSITIVE LOGITS
    0.07
    Character
    0.07
    Books
    0.07
     bast
    0.06
    routeParams
    0.06
     loadChildren
    0.06
     tử
    0.06
     guilty
    0.06
    ABCDEFGHIJKLMNOP
    0.06
    ريل
    0.06
    Act Density 0.001%

    No Known Activations