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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     göster
    -0.08
     economies
    -0.07
     Obviously
    -0.07
     Unsure
    -0.07
    _requires
    -0.07
     shields
    -0.07
     Draw
    -0.07
    余
    -0.07
     Consultants
    -0.07
    _horizontal
    -0.07
    POSITIVE LOGITS
     illumin
    0.06
    MatrixXd
    0.06
    ション
    0.06
    četně
    0.06
     seine
    0.06
    stringstream
    0.06
    .tokens
    0.06
     phái
    0.06
    .margin
    0.05
    cb
    0.05
    Act Density 0.100%

    No Known Activations