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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     waved
    -0.07
     waving
    -0.07
     pursue
    -0.06
    лю
    -0.06
    eração
    -0.06
     Finnish
    -0.06
    ю
    -0.06
    _FINISH
    -0.06
     lugares
    -0.06
    purchase
    -0.06
    POSITIVE LOGITS
     nir
    0.06
     Scan
    0.06
    <Color
    0.06
     Papa
    0.06
     sera
    0.06
     Ital
    0.06
    COPY
    0.06
    cház
    0.06
     nutrient
    0.06
     сторін
    0.06
    Act Density 0.053%

    No Known Activations