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

    Neuronpedia

    INDEX
    Explanations

    hurricanes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ها
    1.07
    ן
    1.05
    将
    1.05
    です
    1.04
    ют
    1.01
    ной
    1.00
     Pasal
    1.00
    いた
    0.99
    об
    0.97
    的市场
    0.97
    POSITIVE LOGITS
    ۔۔
    1.03
    ्ञ
    1.02
    ne
    0.98
    ্স
    0.94
    le
    0.92
    ب
    0.89
    zne
    0.89
    :
    0.89
    ned
    0.88
    ).
    0.87
    Act Density 0.001%

    No Known Activations