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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alsnog
    -0.08
    -0.08
     critères
    -0.08
     banques
    -0.08
    саты
    -0.08
     banker
    -0.07
     Bradley
    -0.07
    医生
    -0.07
    словия
    -0.07
     banque
    -0.07
    POSITIVE LOGITS
    効
    0.12
     eficiencia
    0.12
     effici
    0.11
     efficiënt
    0.11
     효
    0.11
     subcontract
    0.10
    效率
    0.10
     streamlined
    0.10
     outsourcing
    0.10
     eficiência
    0.10
    Act Density 0.023%
    No Known Activations