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

    Neuronpedia

    INDEX
    Explanations

    Politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     معنی
    -0.06
    BL
    -0.06
    gether
    -0.06
    Identity
    -0.06
     zobraz
    -0.06
     preferences
    -0.06
    (Editor
    -0.06
    考虑
    -0.06
     BoxDecoration
    -0.06
     през
    -0.06
    POSITIVE LOGITS
     Athe
    0.07
     singer
    0.07
     Reserve
    0.07
     Elk
    0.07
     narc
    0.07
    ronics
    0.06
     vacancies
    0.06
    izer
    0.06
    ificio
    0.06
     св
    0.06
    Act Density 0.126%

    No Known Activations