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

    Neuronpedia

    INDEX
    Explanations

    Mathematical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಬೇಕ
    -0.08
     Жал
    -0.08
    ಬೇಕು
    -0.08
    Très
    -0.08
     $$$
    -0.08
     Очень
    -0.08
    È
    -0.08
    手续费
    -0.08
    сыз
    -0.07
     ಮುಂದ
    -0.07
    POSITIVE LOGITS
     durchs
    0.08
     catalog
    0.08
     catalogue
    0.08
    enumer
    0.07
     brows
    0.07
     enumer
    0.07
    ిలో
    0.07
    exam
    0.07
     carnival
    0.07
    메
    0.07
    Act Density 0.161%

    No Known Activations