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

    Neuronpedia

    INDEX
    Explanations

    utils

    np_max-act · gemini-2.0-flash

    code related to licensing and copyright information.

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

    The neuron fires on local C/C++ header filenames in #include directives (i.e. quoted “.h” include names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ratio
    -0.07
     Monitoring
    -0.07
    	length
    -0.06
    object
    -0.06
     Swamp
    -0.06
     tuples
    -0.06
    .Month
    -0.06
    _IMAGE
    -0.06
     SSP
    -0.06
    idores
    -0.06
    POSITIVE LOGITS
     trabajar
    0.07
     '))↵
    0.06
     Nederland
    0.06
     Birleşik
    0.06
    835
    0.06
     edil
    0.06
     جع
    0.06
     extraordin
    0.06
    eful
    0.06
     Alonso
    0.06
    Act Density 0.012%

    No Known Activations