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

    Neuronpedia

    INDEX
    Explanations

    foreign language text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    const
    1.06
    fetch
    0.98
    FAQs
    0.95
    him
    0.94
    opin
    0.94
    medicine
    0.93
    Him
    0.93
    respective
    0.91
    recipe
    0.91
    literally
    0.90
    POSITIVE LOGITS
     안
    0.95
     obviously
    0.87
    自
    0.86
     우리가
    0.86
     검
    0.85
     resellers
    0.83
     내가
    0.79
     전
    0.79
     quark
    0.77
     두
    0.77
    Act Density 0.027%

    No Known Activations