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

    Neuronpedia

    INDEX
    Explanations

    European nobility

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens that are part of aristocratic titles and names (e.g. Duchess, Princess, Marie, etc.) indicating European nobility.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MAN
    -0.07
     RN
    -0.06
    aln
    -0.06
     큰
    -0.06
     اد
    -0.06
     contraseña
    -0.06
    лом
    -0.06
     krás
    -0.05
     }];↵↵
    -0.05
    educ
    -0.05
    POSITIVE LOGITS
     courteous
    0.07
    †
    0.06
    执行
    0.06
    -term
    0.06
    ?action
    0.06
    Ta
    0.06
     Abel
    0.06
    預
    0.06
     touted
    0.06
    productId
    0.06
    Act Density 0.011%

    No Known Activations