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

    Neuronpedia

    INDEX
    Explanations

    function declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    franc
    0.41
    ランス
    0.40
     ઓફ
    0.40
     اوكي
    0.40
    モード
    0.39
    莖
    0.39
     нако
    0.39
     ܐ
    0.39
     моделей
    0.39
     clog
    0.39
    POSITIVE LOGITS
    viewDidLoad
    0.71
     viewDidLoad
    0.70
    didReceive
    0.63
     tableView
    0.58
    tableView
    0.58
    touches
    0.54
     view
    0.52
     didReceive
    0.50
     touches
    0.50
    Did
    0.49
    Act Density 0.002%

    No Known Activations