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

    Neuronpedia

    INDEX
    Explanations

    product launch, development, and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.86
    IA
    0.77
    LE
    0.73
    .
    0.68
     diminu
    0.67
     be
    0.66
    ED
    0.64
    LY
    0.63
    ク
    0.63
    ண
    0.62
    POSITIVE LOGITS
     products
    1.12
     продукт
    1.06
     product
    1.04
     ürün
    0.98
     उत्पाद
    0.95
    продук
    0.93
    products
    0.93
     produk
    0.93
     prodotti
    0.92
     продукта
    0.91
    Act Density 0.041%

    No Known Activations