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

    Neuronpedia

    INDEX
    Explanations

    Biographical/historical texts

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric date tokens (years and year‐ranges) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Tut
    -0.07
     Arts
    -0.06
     arts
    -0.06
    laştır
    -0.06
    七
    -0.06
     Pep
    -0.06
     přátel
    -0.06
    기준
    -0.06
     Estimates
    -0.06
    uros
    -0.06
    POSITIVE LOGITS
     browsing
    0.07
     rall
    0.06
    -rule
    0.06
     rematch
    0.06
     dood
    0.06
     disin
    0.06
     clause
    0.06
    igidBody
    0.06
     alm
    0.06
    …↵↵↵
    0.06
    Act Density 0.029%

    No Known Activations