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

    Neuronpedia

    INDEX
    Explanations

    word embeddings code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jury
    -0.09
    _button
    -0.09
    Buttons
    -0.08
     bathroom
    -0.08
    消防
    -0.08
     judicial
    -0.08
     judiciary
    -0.08
     Jury
    -0.08
    法规
    -0.08
     regulatory
    -0.08
    POSITIVE LOGITS
     Hadoop
    0.12
     nltk
    0.10
     embeddings
    0.08
     verkrij
    0.08
     correr
    0.08
     ọrọ
    0.08
    mmat
    0.08
     Flickr
    0.08
    atul
    0.08
     çıkt
    0.08
    Act Density 0.004%

    No Known Activations