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

    Neuronpedia

    INDEX
    Explanations

    command line arguments `argv`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    andled
    1.11
    砰
    1.03
     slamming
    1.03
     deepening
    1.00
    พ์
    1.00
     stormy
    0.99
     upholding
    0.97
    nings
    0.94
     кількість
    0.92
    花生
    0.92
    POSITIVE LOGITS
    an
    1.06
    a
    1.03
    Cette
    1.00
     Normalized
    0.99
    ISS
    0.98
     ис
    0.97
    analyzer
    0.96
    ла
    0.96
     находи
    0.95
    MCA
    0.95
    Act Density 0.000%

    No Known Activations