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

    Neuronpedia

    INDEX
    Explanations

    Chapters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fact
    -0.08
    一家
    -0.08
     broadcaster
    -0.08
    аст
    -0.08
     notor
    -0.08
     instituciones
    -0.07
     réput
    -0.07
    giv
    -0.07
    cpy
    -0.07
    caster
    -0.07
    POSITIVE LOGITS
     subsection
    0.15
    章节
    0.12
     chapter
    0.12
    Chapter
    0.12
     Chapter
    0.11
     chapitre
    0.11
     bölüm
    0.10
     подраздел
    0.10
    章
    0.10
     Abschnitt
    0.10
    Act Density 0.053%

    No Known Activations