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

    Neuronpedia

    INDEX
    Explanations

    of, and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     значит
    0.50
     conseguenza
    0.48
    bezpie
    0.47
    lihat
    0.46
     ಅಂಶ
    0.46
     dlatego
    0.45
    システム
    0.45
    0.45
    respuesta
    0.45
     ആദ്യ
    0.44
    POSITIVE LOGITS
     of
    0.98
    of
    0.92
     thereof
    0.91
     của
    0.88
    ของ
    0.81
     của
    0.75
    ของการ
    0.73
     της
    0.69
     ofthe
    0.68
    នៃ
    0.66
    Act Density 0.286%

    No Known Activations