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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron fires on HTML markup tags (e.g. “<html>”, “<!DOCTYPE html>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _longitude
    -0.07
    _qty
    -0.07
    -country
    -0.07
    `]
    -0.07
    setq
    -0.06
     pracovní
    -0.06
     "");↵↵
    -0.06
     kterou
    -0.06
     ویژ
    -0.06
    итив
    -0.06
    POSITIVE LOGITS
     conquer
    0.07
    	pre
    0.06
    _sent
    0.06
    abis
    0.06
    ussed
    0.06
    ϊ
    0.06
    .diff
    0.06
    	protected
    0.06
    �
    0.06
    amous
    0.06
    Act Density 0.003%

    No Known Activations