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

    Neuronpedia

    INDEX
    Explanations

    words followed by with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    相比
    0.71
    ֔
    0.68
    を務
    0.65
    よかった
    0.65
    为例
    0.65
    그리고
    0.64
    కులు
    0.62
    ഞ്ഞെടു
    0.62
    फु
    0.61
     없고
    0.61
    POSITIVE LOGITS
     with
    6.04
    with
    5.66
     avec
    5.14
    With
    5.03
     With
    4.96
     với
    4.95
     dengan
    4.91
     WITH
    4.72
     עם
    4.50
    WITH
    4.31
    Act Density 3.974%

    No Known Activations