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

    Neuronpedia

    INDEX
    Explanations

    product series or families

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dacă
    0.72
     on
    0.68
    o
    0.66
     jika
    0.64
     dari
    0.58
     February
    0.57
     lawyer
    0.57
     bur
    0.55
     l
    0.55
     doctor
    0.54
    POSITIVE LOGITS
    シリーズ
    0.82
    products
    0.79
     serii
    0.70
    productos
    0.69
    produtos
    0.68
     سلسلة
    0.68
    Produtos
    0.66
    제품
    0.66
    launched
    0.65
    商品の
    0.65
    Act Density 0.153%

    No Known Activations