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

    Neuronpedia

    INDEX
    Explanations

    xml declaration and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wchar
    0.77
     vidhan
    0.74
    ửi
    0.74
    遺跡
    0.73
    Gan
    0.72
    aily
    0.72
    ἥ
    0.71
    权益
    0.71
    лах
    0.71
    핳
    0.71
    POSITIVE LOGITS
     been
    0.76
     vært
    0.67
     gotovo
    0.63
     Matrices
    0.62
     været
    0.62
     работу
    0.62
    ො
    0.61
     pair
    0.60
     sido
    0.60
     be
    0.60
    Act Density 0.002%

    No Known Activations