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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects XML or markup element names (keys) such as “abstract,” “answer,” “appendix,” “article,” “bibliography,” and “book.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    55
    -0.06
    (Convert
    -0.06
    hp
    -0.06
    SON
    -0.06
    oute
    -0.06
    슨
    -0.06
    .</
    -0.06
     ini
    -0.06
    _prop
    -0.06
     wolf
    -0.06
    POSITIVE LOGITS
    极
    0.07
    =yes
    0.07
    _minutes
    0.06
    NSMutableDictionary
    0.06
    DeltaTime
    0.06
    	SDL
    0.06
    >>(
    0.06
    608
    0.06
    <AudioSource
    0.06
    PointCloud
    0.06
    Act Density 0.014%

    No Known Activations