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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash

    This neuron fires on sentence‐ or clause‐level discourse markers and transitional words (e.g. “However,” “But,” “Upon,” “Since,” “Then,” “A,” etc.) that typically appear at the start of new sentences or clauses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    probably
    -0.07
     psychologists
    -0.07
     افزایش
    -0.07
     embroidered
    -0.07
    itions
    -0.07
     practically
    -0.06
     Mandarin
    -0.06
     durability
    -0.06
    -mails
    -0.06
     misuse
    -0.06
    POSITIVE LOGITS
     lex
    0.07
    _Osc
    0.07
    .raw
    0.06
     теч
    0.06
    bron
    0.06
    razione
    0.06
     seus
    0.06
    enção
    0.06
    ้น
    0.06
     avere
    0.06
    Act Density 0.072%

    No Known Activations