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

    Neuronpedia

    INDEX
    Explanations

    accuracy and error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ರಚ
    0.44
     परिचित
    0.43
    autoplay
    0.41
    󠁳
    0.40
     autoplay
    0.40
    ికె
    0.40
    开放
    0.39
     मंत्रियों
    0.39
    countplot
    0.39
    𐰚
    0.39
    POSITIVE LOGITS
     accuracy
    2.73
     Accuracy
    2.45
    Accuracy
    2.44
    accuracy
    2.41
     inaccuracy
    2.30
     accuracies
    2.20
     inaccuracies
    2.14
    精度
    2.13
     accurate
    2.09
    误差
    1.95
    Act Density 0.030%

    No Known Activations