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

    Neuronpedia

    INDEX
    Explanations

    Math questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -period
    -0.07
     pazar
    -0.07
     ForCanBeConvertedToForeach
    -0.07
    Strategy
    -0.06
    institution
    -0.06
    descriptor
    -0.06
     götür
    -0.06
    handleChange
    -0.06
     textStyle
    -0.06
     quantify
    -0.06
    POSITIVE LOGITS
     Stoke
    0.07
     gly
    0.07
    |M
    0.07
     одного
    0.07
    므로
    0.07
    فته
    0.06
    immel
    0.06
     Courts
    0.06
     Orlando
    0.06
     chang
    0.06
    Act Density 0.005%

    No Known Activations