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
     ọsọ
    -0.08
    -night
    -0.08
     menos
    -0.07
    ස්
    -0.07
    حوق
    -0.07
     Wall
    -0.07
    �
    -0.07
     ọgụ
    -0.07
    сылка
    -0.07
     uto
    -0.07
    POSITIVE LOGITS
    事项
    0.08
     പാല
    0.08
     מט
    0.08
     sanitaria
    0.08
    事項
    0.08
    Draft
    0.07
     Draft
    0.07
     सुनिश्चित
    0.07
     provisions
    0.07
     साहित्य
    0.07
    Act Density 0.067%

    No Known Activations