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

    Neuronpedia

    INDEX
    Explanations

    specific types or kinds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Various
    1.01
    Various
    1.01
    various
    0.94
     المختلفة
    0.90
     различных
    0.89
     various
    0.89
     مختلف
    0.87
     различные
    0.86
     различными
    0.83
     berbagai
    0.82
    POSITIVE LOGITS
     kinds
    1.37
     kind
    1.31
    種類の
    1.25
     type
    1.21
     set
    1.19
    类型的
    1.17
     types
    1.16
     soorten
    1.11
    kind
    1.07
     soort
    1.07
    Act Density 0.336%

    No Known Activations