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

    Neuronpedia

    INDEX
    Explanations

    dart code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    桀
    0.43
    ్రియ
    0.41
    Moore
    0.41
    ੧
    0.41
    Ꭻ
    0.40
     lésions
    0.40
    ையு
    0.38
    峽
    0.38
    Private
    0.38
    чү
    0.37
    POSITIVE LOGITS
     Future
    0.91
    Future
    0.85
    bool
    0.80
     late
    0.77
    void
    0.73
    late
    0.70
     void
    0.68
     Widget
    0.68
     TextEditing
    0.68
     bool
    0.67
    Act Density 0.012%

    No Known Activations