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
     caches
    -0.07
     Moral
    -0.07
     Nail
    -0.06
     ок
    -0.06
     taking
    -0.06
     stealing
    -0.06
     shipments
    -0.06
     House
    -0.06
     meanwhile
    -0.06
     göre
    -0.06
    POSITIVE LOGITS
     офици
    0.07
    時代
    0.07
    keeping
    0.07
    ্
    0.06
    ->[
    0.06
    (IService
    0.06
    (clazz
    0.06
     ا
    0.06
    _levels
    0.06
    limits
    0.06
    Act Density 0.107%

    No Known Activations