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

    Neuronpedia

    INDEX
    Explanations

    stories and chapters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    такт
    0.40
    =''
    0.40
     மேம்ப
    0.40
    ${\
    0.39
     broadly
    0.37
     exceeding
    0.37
    咱們
    0.37
     [(
    0.36
    حافظ
    0.36
     [{\
    0.36
    POSITIVE LOGITS
     chapter
    0.56
     chapters
    0.56
     Chapter
    0.56
     CHAPTER
    0.55
    Chapter
    0.54
     capítulos
    0.53
     Kapitel
    0.52
    章节
    0.51
     STORIES
    0.51
    CHAPTER
    0.50
    Act Density 0.036%

    No Known Activations