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

    Neuronpedia

    INDEX
    Explanations

    numbers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    í
    0.89
    é
    0.82
    o
    0.80
    et
    0.78
    ë
    0.75
    st
    0.75
    pl
    0.75
    mo
    0.73
    la
    0.73
    n
    0.73
    POSITIVE LOGITS
    ுமா
    0.92
    鐟
    0.90
     shaver
    0.86
     therewith
    0.81
    aneswar
    0.81
    🧢
    0.81
    ESI
    0.80
    长安
    0.80
     reduc
    0.80
    ังหวัด
    0.80
    Act Density 0.003%

    No Known Activations