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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_max-act · gemini-2.0-flash

    The neuron primarily detects numeric tokens—especially digits or digit sequences used in dates (e.g. years).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Processing
    -0.07
     JSONObject
    -0.06
    (old
    -0.06
     pioneering
    -0.06
     weekend
    -0.06
    ень
    -0.06
    anto
    -0.06
    .Me
    -0.06
     yalnız
    -0.06
     Imports
    -0.06
    POSITIVE LOGITS
    +S
    0.07
     removable
    0.07
    S
    0.06
    РН
    0.06
    .Database
    0.06
    нося
    0.06
    ilm
    0.06
    .Errors
    0.06
     produkt
    0.06
    vit
    0.06
    Act Density 0.026%

    No Known Activations