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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron is strongly triggered by all-caps identifiers (especially C/C++ preprocessor macro names and constant tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     procrast
    -0.07
    etypes
    -0.06
    organizations
    -0.06
     小
    -0.06
     treasurer
    -0.06
    covers
    -0.06
     bạc
    -0.06
    श
    -0.06
     medications
    -0.05
     alphanumeric
    -0.05
    POSITIVE LOGITS
     Meaning
    0.07
     등록
    0.07
    日本
    0.07
     нату
    0.06
    rous
    0.06
    Song
    0.06
    <body
    0.06
    _SYMBOL
    0.06
    Agency
    0.06
    ***↵↵
    0.06
    Act Density 0.046%

    No Known Activations