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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects references to the “Internal Revenue Code” (and its year or section numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Bat
    -0.07
     owl
    -0.06
     접
    -0.06
     Obs
    -0.06
    .gwt
    -0.06
     proxy
    -0.06
    fish
    -0.06
    LESS
    -0.06
    (Game
    -0.06
    답
    -0.06
    POSITIVE LOGITS
    interactive
    0.07
     marching
    0.06
    sensor
    0.06
    autos
    0.06
    煙
    0.06
     Greenville
    0.06
     nev
    0.06
    761
    0.06
     cpt
    0.06
     tegen
    0.06
    Act Density 0.001%

    No Known Activations