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

    Neuronpedia

    INDEX
    Explanations

    Chinese last names

    np_max-act · gemini-2.0-flash

    This neuron detects author name tokens (proper names) in the document metadata.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Petersburg
    -0.07
     characterized
    -0.07
    エル
    -0.07
     Seminar
    -0.07
     ΕΠ
    -0.06
    페
    -0.06
    ETING
    -0.06
     seminar
    -0.06
    minate
    -0.06
    도로
    -0.06
    POSITIVE LOGITS
     лей
    0.07
     GLuint
    0.06
    ?)
    0.06
     crush
    0.06
    .front
    0.06
    legend
    0.06
    quarter
    0.06
    quel
    0.06
    リ
    0.06
     strands
    0.06
    Act Density 0.032%

    No Known Activations