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

    Neuronpedia

    INDEX
    Explanations

    print separators and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Canterbury
    0.38
     Magdeburg
    0.37
    ຄ
    0.35
     المقدم
    0.35
    ტო
    0.34
     مستقل
    0.34
    acetamide
    0.34
     Interment
    0.33
     elementName
    0.33
    မျှ
    0.33
    POSITIVE LOGITS
    produ
    0.47
    parse
    0.42
     fashionable
    0.40
    inner
    0.39
    describe
    0.39
    Perform
    0.39
    info
    0.39
    perform
    0.39
    BASIC
    0.39
    founder
    0.37
    Act Density 0.002%

    No Known Activations