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

    Neuronpedia

    INDEX
    Explanations

    finding textbook chapters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idő
    0.42
    spraak
    0.41
     gestures
    0.39
    cellSize
    0.38
     clinician
    0.38
    TouchEvent
    0.38
     urine
    0.37
     බව
    0.37
     dragState
    0.37
     vibhav
    0.37
    POSITIVE LOGITS
    章节
    0.59
    chapters
    0.57
     chapters
    0.54
     Kapitel
    0.54
    chapter
    0.52
     Find
    0.49
     Chapter
    0.49
    Chapters
    0.49
     chapter
    0.49
     Chapters
    0.49
    Act Density 0.000%

    No Known Activations