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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects proper names (e.g. attorney and party names) in legal‐document headings.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ITER
    -0.07
     persists
    -0.07
    °E
    -0.07
     Trades
    -0.07
    /UI
    -0.07
    ）、
    -0.07
    (Func
    -0.07
     specifics
    -0.06
     Desc
    -0.06
    ازد
    -0.06
    POSITIVE LOGITS
    oved
    0.07
    allow
    0.07
     Schwe
    0.07
    ें↵↵
    0.07
    _visitor
    0.06
    ALLOW
    0.06
     dbname
    0.06
     sare
    0.06
    成员
    0.06
    YN
    0.06
    Act Density 0.013%

    No Known Activations