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

    Neuronpedia

    INDEX
    Explanations

    Historical contexts

    np_max-act · gemini-2.0-flash

    historical figures and dates associated with events.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on Cyrillic-script text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    alo
    -0.07
    かって
    -0.06
     الث
    -0.06
     UW
    -0.06
     plight
    -0.06
     Richard
    -0.06
    fires
    -0.06
    Richard
    -0.06
    mens
    -0.06
    ,lat
    -0.06
    POSITIVE LOGITS
     predominant
    0.06
     fragmentManager
    0.06
     gouver
    0.06
     refunded
    0.06
    (levels
    0.06
     Absolutely
    0.06
     hopes
    0.06
    crete
    0.06
    .assertIsInstance
    0.06
     (::
    0.06
    Act Density 0.027%

    No Known Activations