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

    Neuronpedia

    INDEX
    Explanations

    dataset, labeled data, training data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standing
    0.75
     Standing
    0.68
    Standing
    0.65
     Mechanic
    0.63
     मूर्ति
    0.62
     सर्च
    0.62
     operatives
    0.62
     Searches
    0.61
     Honor
    0.59
     traveller
    0.59
    POSITIVE LOGITS
     dataset
    2.18
    Dataset
    2.08
     Dataset
    2.07
    dataset
    1.95
     datasets
    1.95
     labels
    1.93
    labels
    1.83
     labeled
    1.82
     Labels
    1.77
    数据集
    1.77
    Act Density 1.087%

    No Known Activations