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

    Neuronpedia

    INDEX
    Explanations

    Plural suffixes

    np_max-act · gemini-2.0-flash

    The neuron fires on Automake variable names that declare libraries (i.e. tokens ending in “LIBRARIES” such as lib_LTLIBRARIES or noinst_LIBRARIES).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sog
    -0.07
     Brno
    -0.07
     Inhal
    -0.07
     ominous
    -0.07
    産
    -0.06
     Kata
    -0.06
     leer
    -0.06
     }}">
    -0.06
     tally
    -0.06
    عام
    -0.06
    POSITIVE LOGITS
    	base
    0.07
    CSI
    0.07
    .isNotEmpty
    0.07
     Makeup
    0.06
    Permission
    0.06
     않고
    0.06
     POLIT
    0.06
    .viewModel
    0.06
    名称
    0.06
    .handleError
    0.06
    Act Density 0.001%

    No Known Activations