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

    Neuronpedia

    INDEX
    Explanations

    inline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مبانی
    -0.07
     女
    -0.07
    ._↵↵
    -0.06
     постанов
    -0.06
    림
    -0.06
     libros
    -0.06
    degrees
    -0.06
    Nr
    -0.06
     numbered
    -0.06
    ленно
    -0.06
    POSITIVE LOGITS
    ้แก
    0.07
     tourists
    0.06
     solutions
    0.06
    ائق
    0.06
     zápas
    0.06
    иться
    0.06
     shorter
    0.06
     News
    0.06
     Diagnostic
    0.06
    metro
    0.06
    Act Density 0.000%

    No Known Activations