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

    Neuronpedia

    INDEX
    Explanations

    in addition to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tannins
    1.98
    時期
    1.81
    了很多
    1.77
    ية
    1.74
     Hàm
    1.73
     अधिकारी
    1.69
     allá
    1.68
    てください
    1.68
    ных
    1.67
    ні
    1.67
    POSITIVE LOGITS
    s
    2.34
    त
    2.30
    ে
    2.08
    س
    1.86
    ter
    1.84
    es
    1.82
    ه
    1.73
    aun
    1.70
    데요
    1.66
    oje
    1.57
    Act Density 0.000%

    No Known Activations