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

    Neuronpedia

    INDEX
    Explanations

    hierarchical clustering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    电动
    0.40
    ীর্ণ
    0.39
     namam
    0.39
     +#+
    0.39
    证券投资基金
    0.38
    ट्टे
    0.38
    txtbtn
    0.38
     بو
    0.38
    家长
    0.38
    散射
    0.38
    POSITIVE LOGITS
     clusters
    0.96
     cluster
    0.95
     clustering
    0.95
     clust
    0.93
    clust
    0.89
     Clustering
    0.88
    cluster
    0.87
    clusters
    0.87
    Cluster
    0.86
     Clusters
    0.86
    Act Density 0.014%

    No Known Activations