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

    Neuronpedia

    INDEX
    Explanations

    .date

    np_max-act · gemini-2.0-flash

    The neuron detects date values in document metadata (the “ms.date” front‐matter line and its numeric tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SIP
    -0.07
     Manson
    -0.07
     onemoc
    -0.06
     typedef
    -0.06
     cellar
    -0.06
    .Roles
    -0.06
    RSS
    -0.06
     boh
    -0.06
    _TH
    -0.06
     supplies
    -0.06
    POSITIVE LOGITS
    .date
    0.08
    าง
    0.07
    _elim
    0.06
     прин
    0.06
     hük
    0.06
     decided
    0.06
     roy
    0.06
     clinical
    0.06
    หมาย
    0.06
    िय
    0.06
    Act Density 0.001%

    No Known Activations