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

    Neuronpedia

    INDEX
    Explanations

    code main function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जिल्
    0.38
    thorpe
    0.37
     пас
    0.37
    ченных
    0.37
    телем
    0.37
    antoor
    0.37
    thiophen
    0.36
     Verbesser
    0.35
     ووٹ
    0.35
    lova
    0.35
    POSITIVE LOGITS
     main
    2.14
    main
    2.03
     Main
    1.48
    Main
    1.44
     मुख्य
    1.40
    MAIN
    1.36
    メイン
    1.36
    主
    1.34
     MAIN
    1.32
     hlavní
    1.31
    Act Density 0.034%

    No Known Activations