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

    Neuronpedia

    INDEX
    Explanations

    card games and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liebe
    -0.08
    linux
    -0.08
     aired
    -0.08
     displayed
    -0.07
    Нов
    -0.07
     tripod
    -0.07
     loving
    -0.07
     liefde
    -0.07
     aislamiento
    -0.07
     linux
    -0.07
    POSITIVE LOGITS
    .shuffle
    0.13
     shuffled
    0.13
     shuffle
    0.11
     Shuffle
    0.11
    shuffle
    0.11
    _shuffle
    0.10
    Shuffle
    0.10
    .deck
    0.10
     Deck
    0.09
    Deck
    0.09
    Act Density 0.005%

    No Known Activations