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

    Neuronpedia

    INDEX
    Explanations

    pandemic and war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ać
    1.19
    ت
    1.13
    oC
    1.10
    یف
    1.09
    льным
    1.05
    یتی
    1.05
     mensuales
    1.05
    تك
    1.03
    ições
    1.02
    tku
    1.00
    POSITIVE LOGITS
    .
    1.16
    ↵
    1.05
    <start_of_image>
    0.98
     I
    0.98
    ’
    0.93
    '
    0.92
    |
    0.90
    其他
    0.89
    นาน
    0.89
    ‘
    0.89
    Act Density 0.045%

    No Known Activations