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

    Neuronpedia

    INDEX
    Explanations

    API routes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cyl
    -0.08
     Grat
    -0.08
     Erinnerung
    -0.07
     récomp
    -0.07
     Erinner
    -0.07
    .matrix
    -0.07
    .li
    -0.07
     substr
    -0.07
    慰
    -0.07
     Chamber
    -0.07
    POSITIVE LOGITS
     CRUD
    0.12
    CRUD
    0.12
     deleted
    0.10
     Delete
    0.10
    Delete
    0.10
     deletes
    0.10
    (delete
    0.10
     編集
    0.10
    /Delete
    0.10
    _delete
    0.10
    Act Density 0.004%

    No Known Activations