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

    Neuronpedia

    INDEX
    Explanations

    locations in addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ட்
    1.07
     પારિજા
    1.05
     اسرائیلی
    1.01
    ាច់
    1.00
     flancs
    1.00
    and
    0.98
     значи
    0.98
     Admittedly
    0.96
     aqueles
    0.95
    𝘵
    0.95
    POSITIVE LOGITS
    ené
    1.13
    送料無料
    1.04
    ‖
    0.98
    便于
    0.98
    电子商务
    0.97
    enye
    0.96
    มาะ
    0.95
    berman
    0.94
    ことができます
    0.94
     accordance
    0.94
    Act Density 0.005%

    No Known Activations