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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deviations
    -0.06
     Triumph
    -0.06
     coeffs
    -0.06
     Veterans
    -0.06
     سل
    -0.06
    ajor
    -0.06
     cultivated
    -0.06
     bowel
    -0.06
    ذر
    -0.06
    Trap
    -0.06
    POSITIVE LOGITS
    :data
    0.07
    231
    0.07
    往
    0.06
    點
    0.06
    ":{↵
    0.06
    _gallery
    0.06
     pediatric
    0.06
    sofar
    0.06
    ({↵
    0.06
    晴
    0.06
    Act Density 0.014%

    No Known Activations