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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /of
    -0.07
     مدت
    -0.07
     Wings
    -0.06
     united
    -0.06
     NVIDIA
    -0.06
     Regions
    -0.06
     Customer
    -0.06
     meals
    -0.06
     phủ
    -0.06
     camouflage
    -0.06
    POSITIVE LOGITS
     contagious
    0.07
     قالب
    0.07
     ir
    0.06
    POSE
    0.06
    _regeneration
    0.06
     ทาง
    0.06
    ]+"
    0.06
     NATIONAL
    0.06
    Під
    0.06
     znám
    0.06
    Act Density 0.084%

    No Known Activations