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

    Neuronpedia

    INDEX
    Explanations

    Russian rural localities

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens, especially statistical figures (population counts, years, and other numeric data) in the document.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     promotes
    -0.07
     write
    -0.07
    Tại
    -0.06
     STAT
    -0.06
    umba
    -0.06
     кош
    -0.06
     disturbing
    -0.06
     Pip
    -0.06
     healthy
    -0.06
     Things
    -0.06
    POSITIVE LOGITS
    	Session
    0.07
    	menu
    0.06
    .Vertex
    0.06
    発表
    0.06
    .office
    0.06
    ubishi
    0.06
    unu
    0.06
    .firestore
    0.06
    ��
    0.06
    	Me
    0.06
    Act Density 0.003%

    No Known Activations