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

    Neuronpedia

    INDEX
    Explanations

    coding problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Halo
    -0.07
     Turns
    -0.07
    ardash
    -0.07
     DT
    -0.07
    -services
    -0.07
     Willie
    -0.07
     Longer
    -0.07
    cloud
    -0.06
     Lem
    -0.06
    work
    -0.06
    POSITIVE LOGITS
    _regions
    0.07
     tamamen
    0.06
    BSITE
    0.06
    .walk
    0.06
    روع
    0.06
    ває
    0.05
    rowsing
    0.05
    CHAPTER
    0.05
     zorun
    0.05
     ﺍ
    0.05
    Act Density 0.055%

    No Known Activations