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

    Neuronpedia

    INDEX
    Explanations

    square root

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     квадрат
    0.55
     squaring
    0.49
     quadrada
    0.47
     square
    0.46
     squared
    0.46
     cuadrada
    0.45
     SQUARE
    0.44
     Cube
    0.43
     carré
    0.43
     quadrados
    0.43
    POSITIVE LOGITS
    ();
    0.41
    worthiness
    0.38
     eines
    0.38
    Woo
    0.38
    Latin
    0.37
     congratulated
    0.36
    Stream
    0.35
    Take
    0.35
    گیری
    0.35
    っ
    0.35
    Act Density 0.003%

    No Known Activations