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

    Neuronpedia

    INDEX
    Explanations

    already happening or existing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    お
    1.15
    你
    1.03
    It
    1.02
    お子
    1.00
    多い
    0.98
    Վ
    0.97
    Κ
    0.95
    If
    0.94
    ホテル
    0.94
    You
    0.94
    POSITIVE LOGITS
    ات
    1.32
    ي
    1.13
    та
    1.02
    '
    0.92
    ы
    0.90
    తో
    0.89
    ين
    0.87
    的就是
    0.87
    ată
    0.85
    дын
    0.85
    Act Density 0.013%

    No Known Activations