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

    Neuronpedia

    INDEX
    Explanations

    Deleting/revisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .putExtra
    -0.06
     Pols
    -0.06
    respect
    -0.06
    compat
    -0.06
    AMIL
    -0.06
    _shuffle
    -0.06
    Modules
    -0.06
    간
    -0.06
    _PAD
    -0.06
     whereas
    -0.06
    POSITIVE LOGITS
     çerçev
    0.08
     "~/
    0.07
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.07
    >().
    0.07
    Calculator
    0.06
    .Pos
    0.06
    /task
    0.06
     denying
    0.06
    (receiver
    0.06
    "}),↵
    0.06
    Act Density 0.219%

    No Known Activations