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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     been
    -0.09
     creep
    -0.09
     padrão
    -0.09
     standar
    -0.08
     standa
    -0.07
    Nearly
    -0.07
     staged
    -0.07
     بر
    -0.07
     Ã
    -0.07
     cobr
    -0.07
    POSITIVE LOGITS
     болон
    0.10
    此外
    0.10
     maupun
    0.09
     आणि
    0.09
     কিংবা
    0.09
     和
    0.09
    और
    0.08
    》和
    0.08
     તથા
    0.08
     તેમજ
    0.08
    Act Density 0.438%

    No Known Activations