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 responds to first-person, self-referential expressions (e.g. “I’m,” “I’ve,” “don’t,” “my”) indicating personal feelings or states.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    official
    -0.07
     eden
    -0.07
     gallons
    -0.06
     розум
    -0.06
     \"%
    -0.06
    .getVersion
    -0.06
     cavern
    -0.06
    _UNSUPPORTED
    -0.06
    USTER
    -0.06
     officially
    -0.06
    POSITIVE LOGITS
    음
    0.06
    خصص
    0.06
    بع
    0.06
     sclerosis
    0.06
    -custom
    0.06
     proportions
    0.06
    �다
    0.06
    brook
    0.06
    父亲
    0.06
    iddi
    0.06
    Act Density 0.075%

    No Known Activations