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

    Neuronpedia

    INDEX
    Explanations

    native

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (("
    -0.06
    다
    -0.06
     đem
    -0.06
    .Paint
    -0.06
    )[:
    -0.06
    _mock
    -0.06
     triệu
    -0.06
    ()*
    -0.06
     manages
    -0.06
    292
    -0.06
    POSITIVE LOGITS
     Southampton
    0.07
    arn
    0.07
     Rentals
    0.06
     ром
    0.06
     exhilar
    0.06
    orks
    0.06
    +</
    0.06
    grave
    0.06
    ُم
    0.06
     SHOP
    0.06
    Act Density 0.005%

    No Known Activations