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

    Neuronpedia

    INDEX
    Explanations

    efficient algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Virgin
    -0.09
    /footer
    -0.09
    Ether
    -0.09
     Virgin
    -0.09
     dul
    -0.09
    Magn
    -0.08
     arrows
    -0.08
    vart
    -0.08
    Mary
    -0.08
     magn
    -0.08
    POSITIVE LOGITS
     efficient
    0.15
     Efficient
    0.15
     efficiently
    0.14
     algorithm
    0.13
     Algorithm
    0.12
     effizient
    0.12
    efficient
    0.12
     Algorithms
    0.12
     algorithms
    0.12
     алгорит
    0.12
    Act Density 0.013%

    No Known Activations