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

    Neuronpedia

    INDEX
    Explanations

    government officials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Immutable
    -0.08
     بالفعل
    -0.08
     schon
    -0.08
    _THAN
    -0.08
    ólico
    -0.08
     зарп
    -0.07
     gedr
    -0.07
     ACTIVE
    -0.07
     imperson
    -0.07
     امن
    -0.07
    POSITIVE LOGITS
     Defines
    0.07
     Основ
    0.07
    pdo
    0.07
    PDO
    0.07
     Assets
    0.07
    esson
    0.07
     periodically
    0.07
     Schl
    0.07
     patron
    0.07
    0.07
    Act Density 0.023%
    No Known Activations