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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash

    The neuron detects references to historical dates or time-of-origin phrases (e.g. “dates back to”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    nější
    -0.07
     borough
    -0.06
    �
    -0.06
     ~/
    -0.06
    ))){↵
    -0.06
     together
    -0.06
     Williams
    -0.06
    単
    -0.06
    ooks
    -0.06
    يرة
    -0.06
    POSITIVE LOGITS
    _PIX
    0.07
    латы
    0.07
     så
    0.07
    MEDIA
    0.07
    LG
    0.06
     Derek
    0.06
     mấy
    0.06
     жир
    0.06
    EU
    0.06
     "'");↵
    0.06
    Act Density 0.071%

    No Known Activations