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

    Neuronpedia

    INDEX
    Explanations

    uk market data and cap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    1.93
    া
    1.43
    一个
    1.16
     epochs
    1.13
    সম্প্রতি
    1.12
     всего
    1.11
    ા
    1.09
     intervening
    1.06
    a
    1.06
     ঘট
    1.06
    POSITIVE LOGITS
    ्स
    1.57
    td
    1.52
    ted
    1.40
    swith
    1.21
    tes
    1.21
    ti
    1.18
    𝗹
    1.18
    ting
    1.17
    lii
    1.16
    denly
    1.15
    Act Density 0.058%

    No Known Activations