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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ILD
    0.46
    pist
    0.41
    इ
    0.40
    HK
    0.40
     courage
    0.39
    9
    0.38
    μεν
    0.38
    ॉक्स
    0.38
    MANN
    0.37
     darah
    0.37
    POSITIVE LOGITS
    码
    0.50
    របស់
    0.50
     Servlet
    0.50
    刓
    0.48
    内容
    0.47
     JUnit
    0.46
     โดย
    0.46
    通过
    0.45
    程序
    0.45
    诫
    0.45
    Act Density 0.005%

    No Known Activations