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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bung
    -0.07
     railway
    -0.07
    _Release
    -0.07
     Retrieved
    -0.07
     disadvantages
    -0.06
    75
    -0.06
    GenerationStrategy
    -0.06
    ژه
    -0.06
    .isVisible
    -0.06
     Freight
    -0.06
    POSITIVE LOGITS
     conditioning
    0.06
     stole
    0.06
     )))
    0.06
    /basic
    0.06
    ož
    0.06
     اجرا
    0.06
    dsn
    0.06
    -cap
    0.06
     nghi
    0.06
    ackBar
    0.05
    Act Density 0.090%

    No Known Activations