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

    Neuronpedia

    INDEX
    Explanations

    Scientific/medical publications

    np_max-act · gemini-2.0-flash

    terms associated with medical procedures targeting chronic sinus issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is primarily detecting in-text reference or section identifier tokens (e.g. the alphanumeric IDs and numbers used in citations and section markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	vector
    -0.07
    Dash
    -0.07
    ."\
    -0.07
     example
    -0.06
    EM
    -0.06
    .memory
    -0.06
    INCLUDED
    -0.06
    )['
    -0.06
    BR
    -0.06
    Professor
    -0.06
    POSITIVE LOGITS
    积
    0.07
     Kiev
    0.07
     phận
    0.06
    분
    0.06
    "][$
    0.06
     tul
    0.06
     Vernon
    0.06
    ulling
    0.06
     paddingTop
    0.06
     معت
    0.06
    Act Density 0.009%

    No Known Activations