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

    Neuronpedia

    INDEX
    Explanations

    Code class definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    طور
    -0.08
    .FileSystem
    -0.06
    .isdir
    -0.06
     Pence
    -0.06
    ethical
    -0.06
     Gibson
    -0.06
    .epoch
    -0.06
    HttpRequest
    -0.06
     kaç
    -0.06
     smb
    -0.06
    POSITIVE LOGITS
     tutoring
    0.07
     qualifications
    0.06
     leer
    0.06
    eração
    0.06
    ellidos
    0.06
    (lua
    0.06
    UnitOfWork
    0.06
    аном
    0.06
    .At
    0.06
    operands
    0.06
    Act Density 0.006%

    No Known Activations