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

    Neuronpedia

    INDEX
    Explanations

    repeating

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on occurrences of the word “repeating.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     om
    -0.07
    opsy
    -0.07
     globalization
    -0.07
     HK
    -0.06
    -import
    -0.06
     �
    -0.06
    IZATION
    -0.06
     library
    -0.06
     methane
    -0.06
    라도
    -0.06
    POSITIVE LOGITS
    estimate
    0.06
    ΕΡ
    0.06
    开始
    0.06
     способом
    0.06
     місто
    0.06
    [res
    0.06
     абсолют
    0.06
     <",
    0.06
    .TEST
    0.06
    чер
    0.06
    Act Density 0.006%

    No Known Activations