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

    Neuronpedia

    INDEX
    Explanations

    side

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens that are floating‐point numerals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ircuit
    -0.06
    sembly
    -0.06
     ][
    -0.06
    padding
    -0.06
    trained
    -0.06
    iga
    -0.06
    .driver
    -0.06
    gmt
    -0.06
    �이
    -0.06
    dden
    -0.06
    POSITIVE LOGITS
     siti
    0.07
     
    0.07
     templ
    0.06
     dispon
    0.06
     constituted
    0.06
     Fam
    0.06
     CAT
    0.06
     anale
    0.06
     položky
    0.06
    acity
    0.06
    Act Density 0.000%

    No Known Activations