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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric attribute values (floating‐point numbers) in XML/HTML tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cie
    -0.06
    mock
    -0.06
    QU
    -0.06
    ηγ
    -0.06
     Gap
    -0.06
    .Cor
    -0.06
    bur
    -0.06
    bl
    -0.06
     Supervisor
    -0.06
    	stop
    -0.06
    POSITIVE LOGITS
     Execute
    0.06
    whether
    0.06
     Baz
    0.06
    imei
    0.06
     افزار
    0.06
     Enabled
    0.06
    ,No
    0.06
    <Any
    0.06
    dateFormat
    0.06
     IMG
    0.06
    Act Density 0.003%

    No Known Activations