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

    Neuronpedia

    INDEX
    Explanations

    months and seasons

    np_max-act · gemini-2.0-flash

    the neuron detects temporal markers in date expressions, especially season names (like “spring,” “summer”) and month names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ктив
    -0.07
     Wash
    -0.06
     fungal
    -0.06
     Minimal
    -0.06
    slashes
    -0.06
    _TERM
    -0.06
     Sachs
    -0.06
    ichael
    -0.06
     Headers
    -0.06
    олько
    -0.06
    POSITIVE LOGITS
     göl
    0.07
    erd
    0.07
     consenting
    0.07
    結
    0.06
     truly
    0.06
     WARNING
    0.06
    やる夫
    0.06
    0.06
     █████
    0.06
     आदम
    0.06
    Act Density 0.023%

    No Known Activations