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

    Neuronpedia

    INDEX
    Explanations

    travel dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     модерни
    0.53
     корпу
    0.48
    AVI
    0.48
     опубликован
    0.46
     수원
    0.43
     поді
    0.43
     статье
    0.43
    рами
    0.43
    头部
    0.43
    輕
    0.43
    POSITIVE LOGITS
    場面積
    0.44
     {
    0.42
     roaring
    0.42
    炀
    0.42
    ぜ
    0.42
    ﺭ
    0.42
    )$$
    0.42
    berat
    0.41
     pref
    0.40
     drunken
    0.40
    Act Density 0.001%

    No Known Activations