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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash

    The neuron activates on the lone “A” that heads each answer section (i.e. the “A:” label introducing a reply in the Q&A transcript).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    questions and statements related to mathematical limits and derivatives.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ùng
    -0.07
    .onSubmit
    -0.07
    Uses
    -0.07
     Hyderabad
    -0.06
     кал
    -0.06
     Monad
    -0.06
     callers
    -0.06
     Overrides
    -0.06
    다운
    -0.06
     physique
    -0.06
    POSITIVE LOGITS
    kart
    0.06
     positions
    0.06
    REE
    0.06
    CEE
    0.06
    ,C
    0.06
     ощ
    0.06
     handy
    0.06
     perimeter
    0.06
     Award
    0.06
     anv
    0.06
    Act Density 0.020%

    No Known Activations