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

    Neuronpedia

    INDEX
    Explanations

    getting class name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     особи
    0.45
     stably
    0.40
     शून्य
    0.39
    ദ്ധതി
    0.39
     sparsity
    0.39
    丙
    0.38
    compId
    0.38
    反射
    0.38
     impasse
    0.38
     stalemate
    0.38
    POSITIVE LOGITS
     sulit
    0.41
     Textiles
    0.41
    装饰
    0.40
     Department
    0.39
     Qualifying
    0.39
     Ceramics
    0.39
    Decoration
    0.38
    ೇಳ
    0.37
    Giz
    0.36
    नी
    0.35
    Act Density 0.001%

    No Known Activations