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

    Neuronpedia

    INDEX
    Explanations

    square root calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éroport
    0.49
    Dining
    0.49
    Clothes
    0.47
    Rok
    0.45
    मुना
    0.45
    拼接
    0.44
    ֨
    0.44
     одежда
    0.44
     옷
    0.44
    服装
    0.43
    POSITIVE LOGITS
     sqrt
    1.56
    sqrt
    1.52
     √
    1.27
    msqrt
    1.27
    Sqrt
    1.27
     √(
    1.24
     square
    1.22
     جذر
    1.19
    √
    1.18
     제곱
    1.16
    Act Density 0.042%

    No Known Activations