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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     обращ
    -0.07
     Certain
    -0.07
     recursos
    -0.07
     $
    -0.07
    வே
    -0.07
     destaca
    -0.07
     depreciation
    -0.07
     Recursos
    -0.07
     ofer
    -0.06
    望
    -0.06
    POSITIVE LOGITS
     associations
    0.12
    Associate
    0.10
     ilişk
    0.10
    Association
    0.10
    Associ
    0.10
     asociación
    0.10
    association
    0.10
     asociaciones
    0.10
     Associations
    0.10
     संबंध
    0.10
    Act Density 0.006%

    No Known Activations