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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tres
    0.76
    三次
    0.72
     тре
    0.71
     Jacq
    0.70
    fifth
    0.69
    Tre
    0.69
    Demand
    0.69
     tř
    0.68
     contre
    0.68
     Tres
    0.67
    POSITIVE LOGITS
     लिस्ट
    0.66
     لیست
    0.65
     elenco
    0.62
    onos
    0.62
    cliffe
    0.60
     (...)
    0.60
    ভিউ
    0.59
     Pvt
    0.59
     Lista
    0.59
    ள்ளி
    0.59
    Act Density 0.019%

    No Known Activations