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

    Neuronpedia

    INDEX
    Explanations

    gold standard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    哏
    0.46
    狒
    0.45
    বিনোদন
    0.43
    谍
    0.41
    तंत्र
    0.41
    虺
    0.41
    Interpolator
    0.40
     মাধ
    0.40
     কারাগ
    0.39
     निर्मला
    0.39
    POSITIVE LOGITS
     gold
    2.13
     золо
    1.87
     golden
    1.81
    gold
    1.80
     golds
    1.79
     Gold
    1.78
    Gold
    1.78
     золото
    1.78
     GOLD
    1.73
     altın
    1.66
    Act Density 0.029%

    No Known Activations