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

    Neuronpedia

    INDEX
    Explanations

    dataset names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bottoms
    0.44
     sendMessage
    0.43
     deletes
    0.43
     lashes
    0.39
     Tiktok
    0.39
     yesterday
    0.39
     doo
    0.38
     Sash
    0.38
     summon
    0.38
     erections
    0.38
    POSITIVE LOGITS
    数据集
    0.72
     dataset
    0.69
     datasets
    0.69
    Dataset
    0.67
     benchmark
    0.64
     Dataset
    0.62
    Benchmark
    0.62
    benchmark
    0.61
    开源
    0.61
    Datasets
    0.61
    Act Density 0.137%

    No Known Activations