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

    Neuronpedia

    INDEX
    Explanations

    personal autobiography and responsibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.52
    ك
    1.50
    خ
    1.36
    一
    1.30
    ول
    1.20
    يا
    1.20
    ಮ
    1.16
    ла
    1.15
    አ
    1.13
    ల
    1.11
    POSITIVE LOGITS
    ↵
    1.11
    ни
    0.96
    us
    0.94
    é
    0.90
     personal
    0.90
    ่
    0.86
    0.86
    ur
    0.85
     pribadi
    0.85
    is
    0.82
    Act Density 0.060%

    No Known Activations