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

    Neuronpedia

    INDEX
    Explanations

    kinds of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    这篇文章
    1.98
    This
    1.84
    หนึ่ง
    1.83
     หนึ่ง
    1.76
    inerary
    1.74
    נה
    1.67
     approche
    1.66
    duit
    1.64
    Cette
    1.62
    One
    1.60
    POSITIVE LOGITS
     kinds
    2.87
     types
    2.82
     những
    2.80
     competencies
    2.71
     four
    2.66
     variables
    2.65
     six
    2.64
     classes
    2.60
     commodities
    2.59
     subtypes
    2.58
    Act Density 0.470%

    No Known Activations