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

    Neuronpedia

    INDEX
    Explanations

    American War

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     озеро
    0.61
     memoria
    0.59
     ανάπτυ
    0.59
     이루
    0.59
     службы
    0.58
     iha
    0.58
    亽
    0.58
     ovaj
    0.57
    nj
    0.57
     уди
    0.56
    POSITIVE LOGITS
    2
    0.61
    на
    0.60
    as
    0.58
    chio
    0.56
    я
    0.56
    en
    0.55
    да
    0.55
    ad
    0.54
    by
    0.54
    ar
    0.53
    Act Density 0.002%

    No Known Activations