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

    Neuronpedia

    INDEX
    Explanations

    Greek language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ías
    0.61
    厛
    0.59
     દ્વારા
    0.56
     نیست
    0.55
     नामक
    0.54
    ímp
    0.54
     Лей
    0.54
    гія
    0.54
     означа
    0.53
    ÍA
    0.53
    POSITIVE LOGITS
     π
    0.57
     α
    0.53
     δια
    0.50
     παρα
    0.48
     πι
    0.48
     πα
    0.48
     ανα
    0.48
     εν
    0.47
     համ
    0.47
     κα
    0.46
    Act Density 0.002%

    No Known Activations