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

    Neuronpedia

    INDEX
    Explanations

    lots of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ました
    1.58
    ন
    1.48
    ர்ஸ்
    1.47
    는지
    1.45
    تی
    1.41
    ませんが
    1.41
    唖
    1.41
    不论
    1.39
    te
    1.38
    ları
    1.38
    POSITIVE LOGITS
    ри
    1.76
    ES
    1.66
    es
    1.65
    er
    1.47
    ่อน
    1.46
    в
    1.44
    iv
    1.41
    filled
    1.33
    hog
    1.32
    employed
    1.29
    Act Density 0.038%

    No Known Activations