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

    Neuronpedia

    INDEX
    Explanations

    linear algebra computations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嵃
    0.45
     figurine
    0.45
    诗
    0.44
     इं
    0.42
    سلام
    0.42
    DebuggingMode
    0.42
     רא
    0.41
    प्शन
    0.40
     unut
    0.40
     साब
    0.40
    POSITIVE LOGITS
     computations
    0.73
     computation
    0.70
    LAP
    0.67
     computes
    0.65
     LAP
    0.64
     Comput
    0.63
     algorithms
    0.61
     sparse
    0.60
     computing
    0.59
     Computation
    0.59
    Act Density 0.013%

    No Known Activations