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

    Neuronpedia

    INDEX
    Explanations

    run executable file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    建设项目
    0.42
     pembangunan
    0.41
    生産
    0.40
    ляр
    0.40
     строительства
    0.39
    чер
    0.39
    스트
    0.38
    推定
    0.38
     ساختمان
    0.38
     bouw
    0.38
    POSITIVE LOGITS
    启动
    0.67
     ./
    0.61
    Launching
    0.61
     java
    0.59
     запуска
    0.58
     launch
    0.57
     запусти
    0.56
     launching
    0.55
     launched
    0.54
    dataPath
    0.54
    Act Density 0.014%

    No Known Activations