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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron activates on the publication metadata dates (e.g. the “Decided on <Month> <Day>, <Year>” lines), effectively detecting the decision date header in court‐opinion documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     mining
    -0.06
     clim
    -0.06
     raise
    -0.06
    etrics
    -0.06
     camping
    -0.06
     Jac
    -0.06
     แ
    -0.06
     TOO
    -0.06
     Checker
    -0.06
     Guild
    -0.06
    POSITIVE LOGITS
     Coconut
    0.06
    Lua
    0.06
     môn
    0.06
    Documentation
    0.06
     Scalia
    0.06
    Broadcast
    0.06
     anatomy
    0.06
    _St
    0.06
     Anthem
    0.06
    omedical
    0.06
    Act Density 0.003%

    No Known Activations