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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that signal personal, first-person statements (e.g. “I,” “me,” “my,” subjective qualifiers), i.e. it picks out writer’s self-references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bent
    -0.06
    ontology
    -0.06
     sentence
    -0.06
    Tra
    -0.06
    .Details
    -0.06
    ypse
    -0.06
     petition
    -0.06
    ukes
    -0.06
    _prov
    -0.06
    Camera
    -0.06
    POSITIVE LOGITS
    >_
    0.07
    _FEED
    0.07
    Schedulers
    0.07
     Hãy
    0.07
    =[[
    0.07
     Hil
    0.06
    Pt
    0.06
    scoped
    0.06
    [attr
    0.06
    nech
    0.06
    Act Density 0.025%

    No Known Activations