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

    Neuronpedia

    INDEX
    Explanations

    people and professions

    np_max-act · gemini-2.0-flash

    This neuron primarily detects mentions of company or brand names (proper nouns) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ผล
    -0.07
    ::*;↵
    -0.07
    <Result
    -0.06
     Debt
    -0.05
     схем
    -0.05
    yscale
    -0.05
     пти
    -0.05
     Lars
    -0.05
    initial
    -0.05
     ecstatic
    -0.05
    POSITIVE LOGITS
     meanwhile
    0.08
    düğü
    0.07
    grave
    0.07
     rejecting
    0.07
    xlsx
    0.07
     (.
    0.07
    ビ
    0.07
    ۷
    0.07
    getDate
    0.07
     authorize
    0.06
    Act Density 0.093%

    No Known Activations