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

    Neuronpedia

    INDEX
    Explanations

    for loop iteration range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mosa
    0.45
     patina
    0.44
     bathtub
    0.43
     kool
    0.43
     standalone
    0.43
     aversion
    0.43
    matical
    0.42
    Ya
    0.41
     hydroxyl
    0.41
     Polaris
    0.41
    POSITIVE LOGITS
    枚举
    0.71
    遍历
    0.67
     startIndex
    0.59
    enerbah
    0.56
    প্তাহ
    0.56
    ogni
    0.56
     ہر
    0.55
     tqdm
    0.55
    owels
    0.55
    每一
    0.55
    Act Density 0.443%

    No Known Activations