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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الإسرائيلي
    -0.09
    刑
    -0.09
     NATO
    -0.08
     diplomatic
    -0.08
     اسرائی
    -0.08
    resent
    -0.08
    väl
    -0.08
     agentes
    -0.08
     Charter
    -0.08
    代理
    -0.08
    POSITIVE LOGITS
    _recipe
    0.13
     рецеп
    0.13
     Recipes
    0.13
     Pinterest
    0.12
     Recipe
    0.12
    (recipe
    0.12
    Recipes
    0.12
    recipe
    0.12
     recipe
    0.12
    .recipe
    0.12
    Act Density 0.343%

    No Known Activations