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

    Neuronpedia

    INDEX
    Explanations

    manufacturing and factories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    were
    0.63
    and
    0.53
     d
    0.52
    d
    0.51
    υ
    0.49
    4
    0.48
    ی
    0.47
    the
    0.47
     ma
    0.46
     outcrop
    0.45
    POSITIVE LOGITS
     Factories
    0.45
    綘
    0.45
    బాద్
    0.44
     honti
    0.42
    工場
    0.42
    妗
    0.41
     години
    0.41
     пра
    0.40
    ON
    0.40
    ）。
    0.40
    Act Density 0.001%

    No Known Activations