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

    Neuronpedia

    INDEX
    Explanations

    API create, delete, query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overfitting
    0.42
     negros
    0.41
     acog
    0.40
    vous
    0.39
     sillon
    0.39
     habitudes
    0.39
     Beaux
    0.39
     moitié
    0.39
    ộn
    0.38
     gritty
    0.38
    POSITIVE LOGITS
    查询
    0.96
    delete
    0.93
     delete
    0.93
    查詢
    0.91
    删除
    0.89
     create
    0.84
    Delete
    0.84
     Delete
    0.82
     查询
    0.81
     Create
    0.80
    Act Density 0.036%

    No Known Activations