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

    Neuronpedia

    INDEX
    Explanations

    website code

    np_max-act · gemini-2.0-flash

    The neuron detects XML element names (the words appearing as tags or tag attributes inside angle brackets).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LH
    -0.07
     potentials
    -0.07
     thresholds
    -0.07
     wp
    -0.06
    (instr
    -0.06
    }-
    -0.06
    賀
    -0.06
     pleasures
    -0.06
    ोलन
    -0.06
    __":↵
    -0.06
    POSITIVE LOGITS
    HTTP
    0.07
     inters
    0.07
    _RUNNING
    0.06
    INCREMENT
    0.06
     رئيس
    0.06
     فوق
    0.06
     cyk
    0.06
     occup
    0.06
    .wikipedia
    0.06
    Cream
    0.06
    Act Density 0.013%

    No Known Activations