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

    Neuronpedia

    INDEX
    Explanations

    200

    np_max-act · gemini-2.0-flash

    The neuron activates on the numeric year values (e.g. “2005,” “2010,” “2001–2012”) in source‐file headers, essentially spotting copyright/version date numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SHADOW
    -0.06
    +"'
    -0.06
    Locker
    -0.06
     Suarez
    -0.06
    vi
    -0.06
    _logical
    -0.06
    allax
    -0.06
    .Throw
    -0.06
     Σύ
    -0.06
    _lista
    -0.06
    POSITIVE LOGITS
     climate
    0.07
    stock
    0.07
     Vancouver
    0.07
    consumer
    0.06
     tie
    0.06
    包含
    0.06
    QUENCY
    0.06
    integer
    0.06
    zee
    0.06
     smells
    0.06
    Act Density 0.012%

    No Known Activations