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

    Neuronpedia

    INDEX
    Explanations

    chapter reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     signific
    0.44
     paper
    0.38
     wedge
    0.37
     bond
    0.37
     suit
    0.37
     দেরী
    0.36
     usp
    0.36
    ภูมิ
    0.36
     seu
    0.35
     regions
    0.35
    POSITIVE LOGITS
     chapter
    0.86
     Chapter
    0.73
    Keywords
    0.73
     CHAPTER
    0.73
    Chapter
    0.71
     capítulo
    0.71
     chapitre
    0.70
     chapters
    0.68
     capítulos
    0.68
    CHAPTER
    0.68
    Act Density 0.002%

    No Known Activations