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

    Neuronpedia

    INDEX
    Explanations

    United Kingdom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    1.19
     has
    0.89
     as
    0.88
     is
    0.86
    </i>
    0.85
     Zhuang
    0.82
     Xuan
    0.82
     Valverde
    0.82
     dij
    0.78
     will
    0.77
    POSITIVE LOGITS
    イギリス
    1.28
    英国
    1.24
    ن
    1.20
    LONDON
    1.19
    England
    1.12
    伦敦
    1.12
    อังกฤษ
    1.09
     البريط
    1.07
     영국
    1.05
    id
    1.04
    Act Density 0.074%

    No Known Activations