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

    Neuronpedia

    INDEX
    Explanations

    unlabeled data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onlyOwner
    0.80
     ประก
    0.79
    称号
    0.78
     Анти
    0.78
    काने
    0.77
    功能的
    0.75
    umumkan
    0.75
    incible
    0.75
     Remedies
    0.75
     Funktionen
    0.74
    POSITIVE LOGITS
     data
    3.71
    data
    3.29
    数据
    3.01
     데이터를
    2.99
     Data
    2.96
    データ
    2.93
     datasets
    2.91
     dataset
    2.88
     데이터
    2.88
    データを
    2.85
    Act Density 0.602%

    No Known Activations