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

    Neuronpedia

    INDEX
    Explanations

    Product descriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on capitalized terms—proper names, acronyms, or words beginning with an uppercase letter.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kumar
    -0.06
    OA
    -0.06
    instruction
    -0.06
     Haram
    -0.06
    ��
    -0.06
    Timestamp
    -0.06
    _arr
    -0.06
     economies
    -0.06
    istringstream
    -0.06
    arcy
    -0.06
    POSITIVE LOGITS
     Providing
    0.07
    ;"↵
    0.07
    造成
    0.06
    、《
    0.06
    &view
    0.06
    _most
    0.06
     Effects
    0.06
     möchten
    0.06
     خودش
    0.06
    成了
    0.06
    Act Density 0.332%

    No Known Activations