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

    Neuronpedia

    INDEX
    Explanations

    acronyms

    np_max-act · gemini-2.0-flash

    This neuron activates on uppercase acronyms and abbreviations (e.g., program names or technical acronyms).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    getX
    -0.07
     orth
    -0.07
     IPS
    -0.06
     点
    -0.06
     mism
    -0.06
     pregn
    -0.06
    นม
    -0.06
     TAX
    -0.06
     Magn
    -0.06
    istributor
    -0.06
    POSITIVE LOGITS
     gł
    0.07
    과정
    0.06
     Ships
    0.06
    dac
    0.06
     Khoa
    0.06
    -we
    0.06
    )`
    0.06
    액
    0.06
    _CONTEXT
    0.06
    Sdk
    0.06
    Act Density 0.043%

    No Known Activations