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

    Neuronpedia

    INDEX
    Explanations

    breakdown of how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feeds
    0.76
    Cards
    0.76
     cards
    0.76
     conceito
    0.75
    Voir
    0.73
     نظری
    0.73
    Muito
    0.72
     conceived
    0.70
     fodder
    0.69
    詆
    0.69
    POSITIVE LOGITS
    求め
    0.64
     Departure
    0.63
    ways
    0.61
     স্ট্যান্ড
    0.61
    臨時
    0.61
    وز
    0.60
     दरों
    0.60
     ہفت
    0.60
    tart
    0.58
    Departure
    0.58
    Act Density 0.064%

    No Known Activations