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

    Neuronpedia

    INDEX
    Explanations

    Narrative/Story

    np_max-act · gemini-2.0-flash

    The neuron responds to first‐person narrative language—pronouns like “I” and temporal/discourse markers such as “once,” “but,” “when,” and “then” that structure a personal story.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    vič
    -0.07
     Perf
    -0.06
     Bewert
    -0.06
     vid
    -0.06
    valid
    -0.06
     Initially
    -0.06
     V
    -0.06
    =response
    -0.06
     formul
    -0.06
     pá
    -0.06
    POSITIVE LOGITS
     italiani
    0.06
    terra
    0.06
    еть
    0.06
    imshow
    0.06
     مشهد
    0.06
    بی
    0.06
     proportional
    0.06
     Examiner
    0.06
    ofi
    0.06
    меж
    0.06
    Act Density 0.034%

    No Known Activations