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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric version tokens in C++ include paths (e.g. the “v1”, “v”, or other digits in library header filenames).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    因
    -0.07
    .time
    -0.07
    _"
    -0.06
     let
    -0.06
     engagements
    -0.06
     disconnected
    -0.06
    หาร
    -0.06
    clud
    -0.06
    ETY
    -0.06
    bout
    -0.06
    POSITIVE LOGITS
    량
    0.07
     Uses
    0.06
     FileType
    0.06
    ActionBar
    0.06
     대행
    0.06
     Merk
    0.06
    (gulp
    0.06
    LogFile
    0.06
    _vm
    0.06
     Pioneer
    0.06
    Act Density 0.005%

    No Known Activations