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

    Neuronpedia

    INDEX
    Explanations

    treasure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     افغانستان
    0.62
    वर्धन
    0.59
    नेक
    0.58
     Snowden
    0.57
     incul
    0.56
     LinkedIn
    0.55
     नाव
    0.55
     কং
    0.55
     صہیونی
    0.55
     جاسک
    0.55
    POSITIVE LOGITS
    宝
    0.70
     treasure
    0.70
    寶
    0.68
    treasure
    0.67
     treasured
    0.66
    treas
    0.66
     thánh
    0.61
    brass
    0.57
    寳
    0.57
     Treasure
    0.56
    Act Density 0.000%

    No Known Activations