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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emojis
    -0.09
     emoji
    -0.09
     esports
    -0.08
     ganador
    -0.08
     gagn
    -0.08
     overnight
    -0.08
     Emoji
    -0.08
     kori
    -0.08
     counts
    -0.08
     ಪ್ರಶ
    -0.08
    POSITIVE LOGITS
    Chapter
    0.16
    chapter
    0.15
     Chapter
    0.14
     chapter
    0.14
    .chapter
    0.13
     textbook
    0.12
    章节
    0.12
    教材
    0.12
     પુસ્તક
    0.12
     textbooks
    0.12
    Act Density 0.020%

    No Known Activations