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

    Neuronpedia

    INDEX
    Explanations

    get/return values or elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    会让
    0.44
     conformado
    0.42
    🙏
    0.40
    娱
    0.40
     نکن
    0.40
    交通
    0.39
     participaron
    0.38
    ศิลป
    0.37
     ಸೇವ
    0.37
    让他们
    0.37
    POSITIVE LOGITS
     get
    0.58
     Returns
    0.52
     returns
    0.52
     Get
    0.50
     获取
    0.49
    Get
    0.47
    获得
    0.47
    get
    0.46
    获取
    0.46
     current
    0.45
    Act Density 0.134%

    No Known Activations