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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron fires on standalone numeric tokens in court‐opinion citation strings—especially the “5 TH CIR. R. 47.5” style rule references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kris
    -0.07
    IColor
    -0.06
     cst
    -0.06
    ψης
    -0.06
     Sandy
    -0.06
    _frag
    -0.06
     تجهیزات
    -0.06
    itest
    -0.06
    라피
    -0.06
    (HttpStatus
    -0.06
    POSITIVE LOGITS
     middle
    0.07
    bohydr
    0.07
    amacare
    0.06
    Earlier
    0.06
    Sections
    0.06
    (outfile
    0.06
     Canonical
    0.06
     mango
    0.06
    ,total
    0.06
    >{{$
    0.06
    Act Density 0.003%

    No Known Activations