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

    Neuronpedia

    INDEX
    Explanations

    Decades

    np_max-act · gemini-2.0-flash

    The neuron predominantly fires on numeric date expressions (years, decades, ages) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .oper
    -0.07
     jente
    -0.07
     їм
    -0.07
     pct
    -0.06
     Grid
    -0.06
     order
    -0.06
     Laud
    -0.06
    ?)↵
    -0.06
     occupy
    -0.06
    UTC
    -0.06
    POSITIVE LOGITS
    artisan
    0.07
     queryString
    0.06
    ]='\
    0.06
    因
    0.06
    active
    0.06
     stringByAppending
    0.06
    우스
    0.06
     scheduling
    0.06
     VERIFY
    0.06
    yet
    0.06
    Act Density 0.032%

    No Known Activations