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

    Neuronpedia

    INDEX
    Explanations

    informal writing style

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    łow
    -0.08
    .Batch
    -0.08
     Uttar
    -0.07
    _MSK
    -0.07
     Tổ
    -0.07
    iltro
    -0.07
    ⇌
    -0.07
     setOpen
    -0.07
     miło
    -0.07
     festive
    -0.07
    POSITIVE LOGITS
     Perfect
    0.08
    quarters
    0.07
    foot
    0.07
    .This
    0.07
    Root
    0.06
    landing
    0.06
    restriction
    0.06
    适
    0.06
     Expires
    0.06
    新兴产业
    0.06
    Act Density 0.008%

    No Known Activations