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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wellington
    -0.07
     lav
    -0.07
    _bold
    -0.06
    (clock
    -0.06
     Runnable
    -0.06
    bies
    -0.06
    (View
    -0.06
     INNER
    -0.06
     version
    -0.06
    (Message
    -0.06
    POSITIVE LOGITS
     payday
    0.07
     Ace
    0.07
     Dustin
    0.06
     milfs
    0.06
     повідом
    0.06
     yapım
    0.06
    .async
    0.06
    .flink
    0.06
    .SubItems
    0.06
    igrated
    0.06
    Act Density 0.055%

    No Known Activations