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

    Neuronpedia

    INDEX
    Explanations

    Seasons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Squ
    -0.07
    @login
    -0.06
    README
    -0.06
     depuis
    -0.06
     satisfies
    -0.06
     immature
    -0.06
    fony
    -0.06
    Structure
    -0.06
    SP
    -0.06
    anford
    -0.06
    POSITIVE LOGITS
    على
    0.07
    ूक
    0.06
    ους
    0.06
     bầu
    0.06
    quierda
    0.06
     dads
    0.06
    _server
    0.06
    ับ
    0.06
     زنده
    0.06
     {?
    0.06
    Act Density 0.001%

    No Known Activations