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

    Neuronpedia

    INDEX
    Explanations

    module access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tast
    0.83
     rozd
    0.77
    inins
    0.74
    Hibernate
    0.74
     medži
    0.71
     внимание
    0.68
     красо
    0.68
    érêt
    0.67
    (__('
    0.67
     pelanggan
    0.67
    POSITIVE LOGITS
     OS
    1.04
     os
    1.03
     System
    0.98
    System
    0.91
    Math
    0.91
     Math
    0.91
     Os
    0.90
     math
    0.85
     ОС
    0.82
    math
    0.80
    Act Density 0.224%

    No Known Activations