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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash

    details about historical medical institutions.

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

    This neuron activates on four‐digit numeric tokens representing years (e.g. “1971,” “1985,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     superst
    -0.06
     ();
↵
    -0.06
     PARTIC
    -0.06
     کامپی
    -0.06
    ropy
    -0.06
     Shirt
    -0.06
    ู
    -0.06
     verir
    -0.06
    ি
    -0.06
    غة
    -0.06
    POSITIVE LOGITS
     jobId
    0.07
    lue
    0.07
    อบ
    0.07
    mobx
    0.06
    !</
    0.06
    704
    0.06
     utilise
    0.06
    Boy
    0.06
    /dashboard
    0.06
    ”:
    0.06
    Act Density 0.003%

    No Known Activations