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

    Neuronpedia

    INDEX
    Explanations

    into shorter, groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    로
    1.25
    क
    1.22
    情况下
    1.20
     से
    1.15
    此
    1.12
     この
    1.05
     của
    1.03
     latter
    1.03
    江苏
    1.02
     این
    1.01
    POSITIVE LOGITS
    শিত
    1.04
     swipe
    0.98
    <unused1872>
    0.95
     sulfonic
    0.93
    sortBy
    0.92
    មី
    0.92
    澳
    0.88
     InputMaybe
    0.88
     wom
    0.88
    expandedTitle
    0.88
    Act Density 0.712%

    No Known Activations