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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    The neuron detects XML attribute assignments (the name="…" or property="…" style attributes within XML tags).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    环境
    -0.08
     зат
    -0.07
    	th
    -0.07
     γυνα
    -0.07
    оят
    -0.06
     뜻
    -0.06
    еними
    -0.06
    wow
    -0.06
    	tx
    -0.06
    enderit
    -0.06
    POSITIVE LOGITS
     oxidation
    0.08
    _attr
    0.07
     modeling
    0.06
     modifications
    0.06
     농
    0.06
     biom
    0.06
     dateTime
    0.06
     insects
    0.06
    strar
    0.06
     users
    0.06
    Act Density 0.020%

    No Known Activations