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

    Neuronpedia

    INDEX
    Explanations

    founded on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用于
    0.20
     барои
    0.19
    用来
    0.19
    برای
    0.18
    ють
    0.18
     用于
    0.17
     assurent
    0.17
     Nếu
    0.16
     kanë
    0.16
    لیف
    0.16
    POSITIVE LOGITS
     a
    0.21
     an
    0.21
     interplay
    0.19
     using
    0.19
     teamwork
    0.18
     teknologi
    0.18
     cooperation
    0.17
     technology
    0.17
     veteran
    0.17
     existing
    0.17
    Act Density 0.846%

    No Known Activations