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 detects the beginnings of new articles or major section headings (i.e. document titles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     gắn
    -0.07
    řik
    -0.07
     Guard
    -0.07
    CellValue
    -0.07
     lạnh
    -0.06
    _State
    -0.06
    erala
    -0.06
    achat
    -0.06
     bitch
    -0.06
     demonstrating
    -0.06
    POSITIVE LOGITS
    	↵
    0.06
     ↑
    0.06
    .:.:.:.
    0.06
     spiel
    0.06
     sessionFactory
    0.06
    :ｉ
    0.06
     зак
    0.06
    (Role
    0.06
     ak
    0.06
     WAR
    0.06
    Act Density 0.085%

    No Known Activations