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

    Neuronpedia

    INDEX
    Explanations

    provide information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செய்யப்படும்
    0.66
    時間が
    0.60
    エ
    0.58
    ทุก
    0.56
    过程中
    0.54
    权限
    0.54
    没事
    0.54
    最初の
    0.53
    ハ
    0.52
     документы
    0.52
    POSITIVE LOGITS
     보여
    0.80
     나타
    0.80
     가져
    0.79
     찾아
    0.75
     갖
    0.75
     찾
    0.72
     가지고
    0.72
     만들어
    0.72
     제공
    0.71
     알려
    0.71
    Act Density 0.002%

    No Known Activations