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

    Neuronpedia

    INDEX
    Explanations

    program entry point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olerance
    0.70
     psychologically
    0.68
    omer
    0.66
    iccation
    0.66
    ৌক
    0.65
     innate
    0.63
    าลัย
    0.63
    }\|_{
    0.62
    biggr
    0.62
    foundland
    0.62
    POSITIVE LOGITS
     main
    2.36
     Main
    2.08
    Main
    2.08
    main
    2.08
     MAIN
    1.82
    MAIN
    1.56
    メイン
    1.53
     मुख्य
    1.42
    主
    1.41
     основной
    1.35
    Act Density 0.527%

    No Known Activations