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

    Neuronpedia

    INDEX
    Explanations

    Code documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profile
    -0.07
    жи
    -0.06
     emploi
    -0.06
    Specifications
    -0.06
    ienia
    -0.06
    ISION
    -0.06
     seemed
    -0.06
     marijuana
    -0.06
    Datos
    -0.06
    ERICAN
    -0.06
    POSITIVE LOGITS
     میلی
    0.08
    InnerHTML
    0.07
     opat
    0.07
     напрям
    0.06
     Conclusion
    0.06
    atak
    0.06
     ΑΝ
    0.06
    _substr
    0.06
    """),↵
    0.06
     gerek
    0.06
    Act Density 0.056%

    No Known Activations