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

    Neuronpedia

    INDEX
    Explanations

    population statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Extent
    -0.07
    자인
    -0.06
     colleagues
    -0.06
    Contact
    -0.06
     Ending
    -0.06
     blind
    -0.06
     pointers
    -0.06
     address
    -0.06
     اجرای
    -0.06
    澳
    -0.06
    POSITIVE LOGITS
    inker
    0.07
     mænd
    0.06
    애
    0.06
    ledged
    0.06
    engl
    0.06
    ินค
    0.06
     xã
    0.06
    unger
    0.06
    Лю
    0.06
     yine
    0.06
    Act Density 0.138%

    No Known Activations