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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on structured section headings or numbered list markers (e.g. “1.”, “2.”) typically used to introduce patent or technical-document sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    呼ば
    -0.07
    >Description
    -0.07
     gathers
    -0.06
     Kaf
    -0.06
    }`;↵
    -0.06
    ียม
    -0.06
     SIP
    -0.06
     changer
    -0.06
     успеш
    -0.06
     asylum
    -0.06
    POSITIVE LOGITS
    (CancellationToken
    0.07
    (priv
    0.07
     setTimeout
    0.06
    ToRemove
    0.06
     Preis
    0.06
     tableLayoutPanel
    0.06
     și
    0.06
    did
    0.06
    різ
    0.06
    ρηση
    0.06
    Act Density 0.023%

    No Known Activations