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

    Neuronpedia

    INDEX
    Explanations

    Truncating numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xmlns
    -0.08
     modern
    -0.08
     moderne
    -0.08
     आधुनिक
    -0.08
     década
    -0.08
     infiltr
    -0.08
     reunited
    -0.07
     kennism
    -0.07
     locations
    -0.07
     modernes
    -0.07
    POSITIVE LOGITS
     trunc
    0.12
    .floor
    0.11
    floor
    0.11
    _floor
    0.11
    Floor
    0.10
     floor
    0.10
     truncate
    0.10
     flooring
    0.09
    Nearest
    0.09
    -floor
    0.09
    Act Density 0.038%

    No Known Activations