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

    Neuronpedia

    INDEX
    Explanations

    code quality and testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     učinkov
    -0.08
     sympat
    -0.07
     medan
    -0.07
    ंप
    -0.07
     inefficient
    -0.07
     처
    -0.07
     независимо
    -0.07
    尋
    -0.07
     misunderstand
    -0.07
     ipairs
    -0.07
    POSITIVE LOGITS
     deuda
    0.10
     Debt
    0.09
     debt
    0.09
     أمير
    0.09
     quarant
    0.09
     Calidad
    0.09
    quality
    0.09
     calidad
    0.09
     أمام
    0.09
    _quality
    0.09
    Act Density 0.005%

    No Known Activations