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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash

    This neuron detects date-related expressions, such as month names and day numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     hygiene
    -0.06
     errMsg
    -0.06
     myšlen
    -0.06
     doubled
    -0.06
    ByText
    -0.06
    所以
    -0.06
     Available
    -0.06
    ('~
    -0.06
    avigator
    -0.06
    響
    -0.06
    POSITIVE LOGITS
     aute
    0.07
    reglo
    0.06
     최고
    0.06
    embro
    0.06
     Arabs
    0.06
     finanční
    0.06
     слу
    0.06
    ność
    0.06
     cours
    0.06
    axy
    0.06
    Act Density 0.011%

    No Known Activations