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

    Neuronpedia

    INDEX
    Explanations

    business/financial information

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens that are part of a company’s proper name (brand or organization name).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    onds
    -0.08
    brands
    -0.07
     NY
    -0.07
    len
    -0.07
    ales
    -0.07
    playing
    -0.06
    ocities
    -0.06
    grad
    -0.06
    LEN
    -0.06
    aking
    -0.06
    POSITIVE LOGITS
    .AddScoped
    0.07
     соответ
    0.06
    ']}
    0.06
    awai
    0.06
     بط
    0.06
     оформ
    0.06
     '))↵
    0.06
     affiliate
    0.06
     О
    0.06
     dismant
    0.06
    Act Density 0.026%

    No Known Activations