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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    patri
    0.58
     HN
    0.56
     Sup
    0.55
     Hair
    0.55
     დაბ
    0.54
    pinned
    0.54
     patri
    0.54
    되지
    0.54
     Noon
    0.52
    roadmap
    0.52
    POSITIVE LOGITS
    レストラン
    0.61
    Dol
    0.59
    餐廳
    0.59
    餐厅
    0.57
    داخل
    0.57
    DOL
    0.56
     underground
    0.56
     worse
    0.55
    ంత్రి
    0.55
     restaurant
    0.55
    Act Density 0.000%

    No Known Activations