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

    Neuronpedia

    INDEX
    Explanations

    chapters of content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kür
    0.49
     expliquer
    0.42
    ্নান
    0.41
     दिलाया
    0.41
    ਲਾਂ
    0.40
     রাম
    0.39
     explique
    0.39
    ریح
    0.38
    ├──
    0.38
     شده‌است
    0.37
    POSITIVE LOGITS
     Chapters
    0.86
     chapters
    0.82
     Chapter
    0.76
    chapters
    0.69
    Chapters
    0.68
     chapter
    0.65
    章节
    0.65
    Chapter
    0.64
     CHAPTER
    0.63
     capítulos
    0.63
    Act Density 0.000%

    No Known Activations