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

    Neuronpedia

    INDEX
    Explanations

    recommendations and best practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    之間
    0.43
    Ꮇ
    0.41
     хранения
    0.40
    자기
    0.38
    נה
    0.38
    連続
    0.38
    ਣ
    0.37
    Ꮑ
    0.37
    harmon
    0.37
    季節
    0.37
    POSITIVE LOGITS
     to
    0.64
     that
    0.49
     well
    0.42
     reforms
    0.42
     mejores
    0.41
     ultimately
    0.41
     Grande
    0.41
     Recommend
    0.41
     выйти
    0.40
     recommends
    0.40
    Act Density 0.009%

    No Known Activations