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

    Neuronpedia

    INDEX
    Explanations

    Table of Contents and Chapters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nerfs
    0.26
     toilets
    0.25
     truffle
    0.24
     saute
    0.24
    ပြီး
    0.24
     rhinestone
    0.24
     grudge
    0.24
     poop
    0.24
     wipers
    0.24
     Bạn
    0.24
    POSITIVE LOGITS
    CHAPTER
    0.38
    Chapter
    0.33
     №
    0.33
    page
    0.33
    ES
    0.32
    Page
    0.32
    페이지
    0.32
     CHAPTER
    0.32
     Page
    0.30
    }$
    0.29
    Act Density 0.005%

    No Known Activations