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

    Neuronpedia

    INDEX
    Explanations

    square footage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мыс
    0.78
     Colton
    0.78
     raha
    0.71
    ម្ម
    0.69
     Thro
    0.68
    榴
    0.67
    कल्प
    0.65
    牦
    0.64
     Mackenzie
    0.63
    缥
    0.63
    POSITIVE LOGITS
     square
    5.36
     Square
    4.86
    Square
    4.82
     squares
    4.76
    square
    4.72
     SQUARE
    4.28
     Squares
    4.21
     squared
    4.19
    squares
    4.08
     sq
    4.05
    Act Density 0.449%

    No Known Activations