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

    Neuronpedia

    INDEX
    Explanations

    categories and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாவது
    0.61
    这类
    0.59
     problémy
    0.55
     gençler
    0.55
     仮
    0.55
     ایسا
    0.55
     místo
    0.55
    கம்
    0.55
    ገር
    0.54
    화
    0.54
    POSITIVE LOGITS
     categories
    2.26
     phases
    2.20
     stages
    2.17
     levels
    1.99
     genres
    1.98
     tiers
    1.88
     eras
    1.88
     sectors
    1.88
     modes
    1.86
     types
    1.83
    Act Density 2.714%

    No Known Activations