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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron identifies short uppercase abbreviations or initialisms (acronyms) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    getStatus
    -0.07
    decorators
    -0.07
     businessmen
    -0.06
     yuan
    -0.06
    _BOUNDS
    -0.06
    -know
    -0.06
    .memo
    -0.06
    .navigate
    -0.06
     nob
    -0.06
     صن
    -0.06
    POSITIVE LOGITS
    ")
↵
    0.08
     Milo
    0.07
    ')
↵
    0.07
    ↵    ↵↵
    0.07
    asty
    0.06
    шла
    0.06
     Investment
    0.06
     (-
    0.06
    σταση
    0.06
         ↵
    0.06
    Act Density 0.024%

    No Known Activations