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

    Neuronpedia

    INDEX
    Explanations

    numbers and counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .serialization
    -0.07
    centre
    -0.07
    Compression
    -0.06
    producer
    -0.06
    stractions
    -0.06
    ng
    -0.06
    İ
    -0.06
    norm
    -0.06
    цин
    -0.06
    imulator
    -0.06
    POSITIVE LOGITS
     �
    0.07
     luck
    0.06
     strapon
    0.06
     excerpt
    0.06
    [x
    0.06
    _MAGIC
    0.06
     маш
    0.06
     glimps
    0.06
    іду
    0.06
     سع
    0.06
    Act Density 0.012%

    No Known Activations