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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash

    This neuron detects XML or HTML tags (strings that begin with “<” and end with “>”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nicaragua
    -0.08
     هنگ
    -0.07
     Čer
    -0.06
    icast
    -0.06
     invocation
    -0.06
     EXPORT
    -0.06
    ��
    -0.06
     Initialization
    -0.06
     donc
    -0.06
    BUR
    -0.06
    POSITIVE LOGITS
    vertices
    0.07
    (contents
    0.07
    .Weight
    0.07
    )reader
    0.06
     ندارد
    0.06
    ,input
    0.06
    	contentPane
    0.06
    (typeof
    0.06
     register
    0.06
    (disposing
    0.06
    Act Density 0.001%

    No Known Activations