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

    Neuronpedia

    INDEX
    Explanations

    Machu Picchu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twenties
    0.66
     sonore
    0.63
    ર
    0.59
    étrico
    0.58
     значення
    0.58
    นี้
    0.57
    npm
    0.57
    𝑜
    0.57
     humanos
    0.57
     mercantil
    0.57
    POSITIVE LOGITS
     been
    0.72
     posed
    0.70
    ा
    0.65
    اء
    0.64
     sorti
    0.61
    ά
    0.61
    en
    0.58
    ाना
    0.58
    ότητα
    0.57
     chargés
    0.55
    Act Density 0.004%

    No Known Activations