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

    Neuronpedia

    INDEX
    Explanations

    a or an

    np_max-act · gemini-2.0-flash

    specific company names related to the chemical industry.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is specifically detecting the standalone indefinite article “a.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _FREE
    -0.07
    ουμε
    -0.06
    ificial
    -0.06
     DUI
    -0.06
    λίου
    -0.06
    quares
    -0.06
    _inf
    -0.06
    andFilterWhere
    -0.06
    ْت
    -0.06
    ὲ
    -0.06
    POSITIVE LOGITS
     subpo
    0.08
     operated
    0.07
    .toString
    0.07
     repr
    0.06
     podrob
    0.06
     später
    0.06
    _↵↵
    0.06
     son
    0.06
     condu
    0.06
    вся
    0.06
    Act Density 0.014%

    No Known Activations