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 fires on tokens that form calendar dates (e.g. day+month or month+year mentions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    1
    -0.06
     ця
    -0.06
    abox
    -0.06
    2
    -0.06
    ik
    -0.06
    leston
    -0.06
     Yin
    -0.06
    ann
    -0.06
    els
    -0.06
    und
    -0.06
    POSITIVE LOGITS
     August
    0.08
    .Direction
    0.07
     September
    0.07
    _construct
    0.07
    September
    0.07
     bisexual
    0.06
     March
    0.06
     august
    0.06
     Jul
    0.06
     December
    0.06
    Act Density 0.038%

    No Known Activations