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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cupcakes
    -0.09
     strawberries
    -0.08
     bagu
    -0.08
    😍
    -0.08
     pizzas
    -0.08
     crou
    -0.08
     견
    -0.08
    821
    -0.08
     yoghurt
    -0.08
     peaches
    -0.08
    POSITIVE LOGITS
     Ministry
    0.13
     администрации
    0.11
     authorities
    0.11
    部门
    0.11
     autorités
    0.10
     autoridades
    0.10
     ministry
    0.10
     وزارة
    0.10
    所在
    0.10
    运营
    0.10
    Act Density 0.065%

    No Known Activations