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

    Neuronpedia

    INDEX
    Explanations

    reason

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of the word "reason," especially in explanatory phrases like "there’s a reason why."

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    gré
    -0.07
     Blitz
    -0.07
    #index
    -0.07
     riot
    -0.07
    .cod
    -0.07
     serialization
    -0.06
     для
    -0.06
    .Persistent
    -0.06
    Twig
    -0.06
    패
    -0.06
    POSITIVE LOGITS
     neb
    0.07
    tı
    0.06
     金
    0.06
     místě
    0.06
     Draws
    0.06
     Arist
    0.06
    )':
    0.06
     colum
    0.06
     legally
    0.06
     HDC
    0.06
    Act Density 0.008%

    No Known Activations