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

    Neuronpedia

    INDEX
    Explanations

    formal or technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ять
    -0.07
    ial
    -0.07
    дами
    -0.06
    agr
    -0.06
    ệu
    -0.06
    (manager
    -0.06
    rapid
    -0.06
    ثمان
    -0.06
    裡
    -0.06
    identify
    -0.06
    POSITIVE LOGITS
     lob
    0.08
     leased
    0.07
     suspicious
    0.07
    yms
    0.06
     racket
    0.06
     Brook
    0.06
    .faces
    0.06
    _RESP
    0.06
     COMMON
    0.06
     shutdown
    0.06
    Act Density 0.000%

    No Known Activations