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

    Neuronpedia

    INDEX
    Explanations

    code and models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     बैठक
    -0.09
    .into
    -0.08
    ições
    -0.08
    (Canvas
    -0.08
     दस्त
    -0.08
    議
    -0.08
     कहानी
    -0.08
    "&
    -0.08
     reuniões
    -0.08
     व्यापार
    -0.08
    POSITIVE LOGITS
     nltk
    0.13
     trained
    0.12
     pretrained
    0.12
     classifiers
    0.10
    -trained
    0.10
     NLP
    0.10
    trained
    0.10
     sklearn
    0.09
     classifier
    0.09
     Detox
    0.09
    Act Density 0.012%

    No Known Activations