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

    Neuronpedia

    INDEX
    Explanations

    ore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )=(
    -0.06
    خي
    -0.06
    _cuda
    -0.06
     ازدواج
    -0.06
     #{
    -0.06
     pus
    -0.06
    _rwlock
    -0.06
    над
    -0.06
    (sqrt
    -0.06
    (system
    -0.06
    POSITIVE LOGITS
     ~~
    0.07
     Montana
    0.06
     slicing
    0.06
     briefing
    0.06
          
    0.06
     Baseball
    0.06
    919
    0.06
    �
    0.06
     bei
    0.06
    いで
    0.06
    Act Density 0.004%

    No Known Activations