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

    Neuronpedia

    INDEX
    Explanations

    expect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toString
    -0.07
    /q
    -0.06
     quá
    -0.06
    Children
    -0.06
     sigmoid
    -0.06
    >("
    -0.06
     Classe
    -0.06
     children
    -0.06
    .Must
    -0.06
     nationalists
    -0.06
    POSITIVE LOGITS
     expect
    0.08
     YORK
    0.07
    (report
    0.07
    lama
    0.07
     Veter
    0.07
    _watch
    0.07
    ック
    0.06
    tık
    0.06
    aptops
    0.06
    odata
    0.06
    Act Density 0.006%

    No Known Activations