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

    Neuronpedia

    INDEX
    Explanations

    reduce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initialized
    -0.07
    lie
    -0.07
     gotten
    -0.07
     stepping
    -0.06
     giao
    -0.06
     khởi
    -0.06
    *))
    -0.06
     communicates
    -0.06
     integerValue
    -0.06
    _DLL
    -0.06
    POSITIVE LOGITS
     reduce
    0.13
     reduced
    0.11
     Reduce
    0.10
    reduce
    0.10
     reduces
    0.10
     reduction
    0.09
    減
    0.09
     reductions
    0.09
     Reduced
    0.09
    Reduc
    0.08
    Act Density 0.050%

    No Known Activations