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

    Neuronpedia

    INDEX
    Explanations

    empires Romans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    پیش
    0.41
     الوطن
    0.40
    ol
    0.40
    众多
    0.38
    主角
    0.37
     enseignants
    0.37
     ଏ
    0.37
     گرم
    0.36
    喝
    0.36
    窈
    0.36
    POSITIVE LOGITS
     పొంద
    0.46
     Dieter
    0.44
     calend
    0.42
    )";
    0.42
    ◐
    0.41
    𒄑
    0.41
    вань
    0.40
    Ѡ
    0.40
    kün
    0.40
     speculation
    0.40
    Act Density 0.001%

    No Known Activations