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

    Neuronpedia

    INDEX
    Explanations

    **breakdown**

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rupees
    0.66
     Imran
    0.65
     Wanita
    0.63
     Aldi
    0.62
     uang
    0.62
     Tesco
    0.61
    UpInside
    0.61
    ς
    0.61
     Rs
    0.61
     Walmart
    0.61
    POSITIVE LOGITS
    色彩
    0.59
    できる
    0.58
     केवळ
    0.57
    nutrient
    0.54
    これにより
    0.54
    いた
    0.53
    compatible
    0.52
    設計
    0.51
    뛰
    0.51
    লাপ
    0.50
    Act Density 0.000%

    No Known Activations