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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric date markers (years or century designations) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     saves
    -0.07
     bien
    -0.07
    -document
    -0.06
    เฟ
    -0.06
    ,O
    -0.06
    saved
    -0.06
     persuade
    -0.06
    ٬
    -0.06
    從
    -0.06
     impass
    -0.06
    POSITIVE LOGITS
     ange
    0.06
     전용
    0.06
     제작
    0.06
    :+
    0.06
     eyebrows
    0.06
     разработ
    0.06
     zel
    0.06
    """
    0.06
    .latest
    0.06
    WhatsApp
    0.06
    Act Density 0.023%

    No Known Activations