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

    Neuronpedia

    INDEX
    Explanations

    delete or removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dressing
    0.46
     dressing
    0.43
     dressings
    0.41
    dressing
    0.41
     crea
    0.38
    getStock
    0.38
    ೈಸ
    0.37
     nouvelles
    0.37
     création
    0.37
     получать
    0.37
    POSITIVE LOGITS
     deletion
    2.14
     deleting
    2.05
     deletes
    1.99
    删除
    1.98
    Deletion
    1.98
     delete
    1.96
     Delete
    1.95
    Delete
    1.92
    Deleting
    1.90
     删除
    1.90
    Act Density 0.056%

    No Known Activations