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 detects honorific titles (e.g. “Mr.”, “Ms.”) before person names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vergence
    -0.06
    Sup
    -0.06
    яс
    -0.06
     Cartesian
    -0.06
    Boot
    -0.06
    スレ
    -0.06
    .drag
    -0.05
    철
    -0.05
     TK
    -0.05
     Agenda
    -0.05
    POSITIVE LOGITS
     teil
    0.07
     Serious
    0.07
     everlasting
    0.07
    พย
    0.07
     للم
    0.07
    _paper
    0.06
     ahead
    0.06
    jest
    0.06
     exhaustive
    0.06
    earable
    0.06
    Act Density 0.005%

    No Known Activations