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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mull
    -0.07
     mosques
    -0.07
     νο
    -0.06
     mk
    -0.06
    мит
    -0.06
     объяс
    -0.06
    *z
    -0.06
     Hàng
    -0.06
     програм
    -0.06
     подготов
    -0.06
    POSITIVE LOGITS
    AGEMENT
    0.07
     más
    0.06
    Author
    0.06
     sah
    0.06
    during
    0.06
     besten
    0.06
     Reached
    0.06
     staples
    0.06
    نی
    0.06
    (Scene
    0.06
    Act Density 0.003%

    No Known Activations