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

    Neuronpedia

    INDEX
    Explanations

    epic quests and fantasy characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    資本
    0.58
    社會
    0.57
    资本
    0.53
     специ
    0.48
    集体
    0.47
     setores
    0.47
     ইয়াহিয়া
    0.47
    設立
    0.46
    溦
    0.46
    ференциа
    0.46
    POSITIVE LOGITS
     unto
    0.54
     ancient
    0.51
     Horn
    0.50
     Al
    0.48
    al
    0.48
     regal
    0.48
     thee
    0.47
     sorrow
    0.47
     shore
    0.47
     Ar
    0.46
    Act Density 0.001%

    No Known Activations