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

    Neuronpedia

    INDEX
    Explanations

    setting up event listeners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    function
    0.47
    func
    0.40
     let
    0.39
    void
    0.39
     function
    0.38
    Ley
    0.38
    Function
    0.38
     increment
    0.37
    Su
    0.36
     ×
    0.36
    POSITIVE LOGITS
     새로운
    0.46
    新的
    0.45
     പുതിയ
    0.45
     object
    0.44
     புதிய
    0.43
     acest
    0.43
    object
    0.42
     جديدة
    0.42
     новый
    0.42
     nuova
    0.42
    Act Density 0.000%

    No Known Activations