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

    Neuronpedia

    INDEX
    Explanations

    Johns Hopkins University or Hopkins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不然
    2.64
    дца
    2.62
    కు
    2.62
     swath
    2.46
    вання
    2.43
    jších
    2.42
    ब्दिक
    2.40
    ंगाना
    2.39
    いない
    2.37
     жить
    2.36
    POSITIVE LOGITS
    ار
    3.35
    ্স
    2.91
    з
    2.78
    y
    2.69
    тип
    2.66
    ্সের
    2.65
    țial
    2.59
     parseFloat
    2.59
    os
    2.59
    ارك
    2.57
    Act Density 0.001%

    No Known Activations