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

    Neuronpedia

    INDEX
    Explanations

    narrowly construed laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     성능
    0.73
    такт
    0.73
    高性能
    0.71
     مدير
    0.70
    ృద్ధి
    0.68
     Lifestyle
    0.67
    Scrolling
    0.67
     productividad
    0.67
    ಯ್
    0.66
     playlists
    0.64
    POSITIVE LOGITS
     laws
    2.85
     legal
    2.68
     law
    2.62
    法律
    2.40
     Laws
    2.39
    Legal
    2.28
    legal
    2.24
    laws
    2.23
     Legal
    2.21
    Laws
    2.20
    Act Density 0.477%

    No Known Activations