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

    Neuronpedia

    INDEX
    Explanations

    requests and formal communication

    np_max-act · gemini-2.0-flash

    The neuron detects words used in polite requests for the issuance or provision of an official document or pass (e.g. “request,” “issuance”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    hold
    -0.06
     Pie
    -0.06
    Wrap
    -0.06
     Bake
    -0.06
     Cơ
    -0.06
     Fork
    -0.06
     gint
    -0.06
     Pig
    -0.06
    bootstrap
    -0.06
     Hand
    -0.06
    POSITIVE LOGITS
    .union
    0.07
    灰
    0.06
     [<
    0.06
     alertDialog
    0.06
    ीवन
    0.06
    DEN
    0.06
     일본
    0.06
    $msg
    0.06
    .den
    0.06
    ullah
    0.06
    Act Density 0.039%

    No Known Activations