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

    Neuronpedia

    INDEX
    Explanations

    @ron

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of the slash‐delimited signature or routing lines in corporate email headers (e.g. name/department/company markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     paddingLeft
    -0.07
    _ONE
    -0.07
     Reco
    -0.07
    που
    -0.06
    culated
    -0.06
    薄
    -0.06
    adera
    -0.06
    ären
    -0.06
    (SP
    -0.06
    ép
    -0.06
    POSITIVE LOGITS
     ipt
    0.07
    _<
    0.07
     heals
    0.07
     Chaos
    0.07
    :".$
    0.07
     especial
    0.06
    ...");↵↵
    0.06
     optimize
    0.06
     achieves
    0.06
     click
    0.06
    Act Density 0.002%

    No Known Activations