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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash

    The neuron activates on date/time expressions (month names and numeric dates/years).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .keyword
    -0.07
     Taxi
    -0.06
     Humanity
    -0.06
     formula
    -0.06
     Skinner
    -0.06
     ecstasy
    -0.06
    kowski
    -0.06
     Ike
    -0.06
     Didn
    -0.06
    的地
    -0.06
    POSITIVE LOGITS
     anzeigen
    0.06
    	cont
    0.06
    uction
    0.06
    .Db
    0.06
     aktiv
    0.06
    .clicked
    0.06
    .VK
    0.06
    pluck
    0.06
     ἀ
    0.06
    祥
    0.06
    Act Density 0.038%

    No Known Activations