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

    Neuronpedia

    INDEX
    Explanations

    predicted probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestData
    0.79
     congrat
    0.74
     Bucks
    0.71
     Symmetry
    0.71
     duomen
    0.71
    रियर
    0.71
    जिंग
    0.71
    ņi
    0.71
    💍
    0.71
     tester
    0.70
    POSITIVE LOGITS
     canh
    0.87
     اليوم
    0.81
    מים
    0.76
     나온
    0.76
    wasser
    0.75
     malades
    0.75
     suisse
    0.75
     қ
    0.74
     eosin
    0.72
    აწ
    0.72
    Act Density 0.072%

    No Known Activations