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

    Neuronpedia

    INDEX
    Explanations

    pair

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bowling
    0.61
    ,<
    0.60
    Helm
    0.59
     lumineux
    0.59
     belladone
    0.58
    Bowling
    0.58
    ègre
    0.57
     Helmet
    0.57
     sillonné
    0.55
     réseau
    0.54
    POSITIVE LOGITS
    Pairs
    0.61
    pair
    0.61
     pairs
    0.61
    对其
    0.60
     pair
    0.60
     Pair
    0.58
    pairs
    0.58
    PAIR
    0.58
     zoveel
    0.57
    Pair
    0.55
    Act Density 0.002%

    No Known Activations