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

    Neuronpedia

    INDEX
    Explanations

    years, dates, or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fehér
    0.96
    racción
    0.94
    􀂾
    0.93
    ൫
    0.93
     tambien
    0.93
    ▭
    0.92
     También
    0.92
    también
    0.92
     lutego
    0.92
     ristorante
    0.92
    POSITIVE LOGITS
    ing
    0.69
     just
    0.66
    ed
    0.62
     di
    0.62
     without
    0.62
     Pres
    0.61
     (
    0.60
    e
    0.60
     Gran
    0.59
     Prim
    0.58
    Act Density 0.019%

    No Known Activations