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

    Neuronpedia

    INDEX
    Explanations

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     penetrated
    0.84
     Calculated
    0.81
     vuelta
    0.80
     recalculated
    0.79
     громад
    0.79
     많
    0.78
     regreso
    0.77
     Kräfte
    0.77
     그렇지
    0.77
     Vorteile
    0.76
    POSITIVE LOGITS
    function
    2.56
     function
    2.29
    class
    1.95
    async
    1.75
    def
    1.74
     class
    1.73
    const
    1.71
    func
    1.55
    Function
    1.54
     Function
    1.43
    Act Density 0.262%

    No Known Activations