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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    employee
    -0.07
     e
    -0.07
    @WebServlet
    -0.06
     address
    -0.06
     outpost
    -0.06
     pog
    -0.06
     Folding
    -0.06
     setUser
    -0.06
     lis
    -0.06
     (_,
    -0.06
    POSITIVE LOGITS
     मत
    0.07
    UPLOAD
    0.06
    苗
    0.06
    alım
    0.06
     Believe
    0.06
    ังน
    0.06
    99
    0.06
     справж
    0.06
     ninguna
    0.06
    [code
    0.06
    Act Density 0.030%

    No Known Activations