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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VALID
    -0.08
     openings
    -0.07
    čné
    -0.07
     spinning
    -0.07
     MainForm
    -0.07
    Pick
    -0.07
     Lane
    -0.07
    visit
    -0.07
     Loader
    -0.06
     heed
    -0.06
    POSITIVE LOGITS
    ##
    0.06
    utorial
    0.06
     mg
    0.06
    Knowledge
    0.06
    QT
    0.06
     fb
    0.06
    erva
    0.06
     استرات
    0.06
    ichert
    0.06
    文献
    0.06
    Act Density 0.001%

    No Known Activations