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

    Neuronpedia

    INDEX
    Explanations

    table summarizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     twos
    0.69
     two
    0.67
     novels
    0.60
    neb
    0.59
     Arduino
    0.58
     многочис
    0.57
    threaded
    0.56
    ひとつ
    0.55
     webpages
    0.55
     वेगवेग
    0.55
    POSITIVE LOGITS
     table
    0.99
     Table
    0.89
    表格
    0.88
    Table
    0.88
     الجدول
    0.85
    table
    0.83
    Tabla
    0.83
     جدول
    0.82
    表
    0.77
    tabla
    0.75
    Act Density 0.110%

    No Known Activations