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

    Neuronpedia

    INDEX
    Explanations

    descriptive qualities or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    二是
    0.40
    楼主
    0.40
    ...),
    0.39
    )、
    0.38
    :");
    0.38
    ",[
    0.38
     ću
    0.38
    搡
    0.37
    enschap
    0.37
    အစား
    0.37
    POSITIVE LOGITS
    ↵↵↵↵
    1.19
    ↵↵↵
    1.10
    ↵↵↵↵↵
    1.08
    ៕
    1.02
    ↵↵↵↵↵↵↵
    1.02
    ↵↵↵↵↵↵
    0.94
    ↵↵↵↵↵↵↵↵↵↵↵
    0.91
    ↵↵↵↵↵↵↵↵
    0.91
    ↵↵↵↵↵↵↵↵↵↵
    0.87
    ↵↵↵↵↵↵↵↵↵
    0.86
    Act Density 0.166%

    No Known Activations