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

    Neuronpedia

    INDEX
    Explanations

    article body content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    몸
    0.48
    身体
    0.46
     ശരീ
    0.46
     ശരീര
    0.45
    ร่างกาย
    0.44
    cL
    0.43
    身體
    0.43
    Lem
    0.41
    hôpital
    0.41
    粪
    0.40
    POSITIVE LOGITS
    ">(
    0.43
     content
    0.42
    скетбол
    0.40
     imaging
    0.40
     extracted
    0.40
     forecasting
    0.39
    ↵↵
    0.39
     색
    0.39
     zaw
    0.39
     内容
    0.38
    Act Density 0.006%

    No Known Activations