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

    Neuronpedia

    INDEX
    Explanations

    subject and title headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     butyl
    0.49
     intestines
    0.46
     acolo
    0.45
     francés
    0.42
    ुए
    0.42
     chinos
    0.42
     alcohols
    0.42
     infrastrukt
    0.41
     sozialen
    0.40
     legumes
    0.40
    POSITIVE LOGITS
    title
    0.63
     title
    0.61
    标题
    0.60
     headline
    0.59
    titulo
    0.58
     제목
    0.56
     शीर्षक
    0.56
     Headline
    0.55
    TITLE
    0.54
    Title
    0.52
    Act Density 0.203%

    No Known Activations