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

    Neuronpedia

    INDEX
    Explanations

    /local

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oppon
    -0.08
     здат
    -0.06
    γκε
    -0.06
     descri
    -0.06
    .writ
    -0.06
    ilib
    -0.06
    існо
    -0.06
     teş
    -0.06
    んで
    -0.06
     cultiv
    -0.05
    POSITIVE LOGITS
    /local
    0.08
    /autoload
    0.07
    ικού
    0.07
    /github
    0.07
     drones
    0.07
    AS
    0.06
    ropol
    0.06
     bik
    0.06
    igh
    0.06
     Soda
    0.06
    Act Density 0.001%

    No Known Activations