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

    Neuronpedia

    INDEX
    Explanations

    subdirectories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uros
    -0.07
     verge
    -0.07
    ตาม
    -0.06
     histograms
    -0.06
    _house
    -0.06
    电影
    -0.06
     run
    -0.06
    /front
    -0.06
    .Scene
    -0.06
     February
    -0.06
    POSITIVE LOGITS
     gọn
    0.07
     resembling
    0.06
    rpc
    0.06
    çe
    0.06
     Rewards
    0.06
     capacity
    0.06
    ními
    0.06
    setDescription
    0.06
     funkc
    0.06
    ्मक
    0.06
    Act Density 0.007%

    No Known Activations