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

    Neuronpedia

    INDEX
    Explanations

    passage

    np_max-act · gemini-2.0-flash

    This neuron activates on the literal word “Passage.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .len
    -0.07
    /index
    -0.07
     Min
    -0.07
    345
    -0.07
    ;\
    -0.06
     mph
    -0.06
     Client
    -0.06
    ①
    -0.06
    1
    -0.06
    %
    -0.06
    POSITIVE LOGITS
     passage
    0.15
     passages
    0.13
     Passage
    0.12
     doprov
    0.10
    uge
    0.08
    age
    0.08
    anse
    0.08
    аче
    0.08
    ще
    0.08
    cce
    0.07
    Act Density 0.006%

    No Known Activations