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

    Neuronpedia

    INDEX
    Explanations

    grade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vanessa
    -0.07
     Sunset
    -0.07
     сторон
    -0.06
     пот
    -0.06
     vliv
    -0.06
    Discussion
    -0.06
    神
    -0.06
     سیاست
    -0.06
    Network
    -0.06
     dispon
    -0.06
    POSITIVE LOGITS
     grade
    0.21
     Grade
    0.17
    -grade
    0.15
    Grade
    0.15
     grades
    0.15
     Grades
    0.13
     graded
    0.11
    _grade
    0.11
     grading
    0.11
    grade
    0.11
    Act Density 0.008%

    No Known Activations