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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lu
    -0.07
     Yön
    -0.07
     q
    -0.06
     director
    -0.06
    (pop
    -0.06
     como
    -0.06
    .fp
    -0.06
     समय
    -0.06
    _page
    -0.06
     realized
    -0.06
    POSITIVE LOGITS
    ODULE
    0.07
     unserialize
    0.07
    egrate
    0.07
    出
    0.07
     Ply
    0.06
     weekday
    0.06
    upgrade
    0.06
    Deadline
    0.06
    _BUCKET
    0.06
     functor
    0.06
    Act Density 0.001%

    No Known Activations