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
     Chatt
    -0.08
     п
    -0.07
     д
    -0.07
     occupancy
    -0.07
    ("(%
    -0.07
     cannabinoids
    -0.06
     campus
    -0.06
     sund
    -0.06
     cocoa
    -0.06
    ुध
    -0.06
    POSITIVE LOGITS
    -author
    0.07
     없
    0.07
    itical
    0.06
    THON
    0.06
     tỷ
    0.06
    _ray
    0.06
     못
    0.06
     nephew
    0.06
     latin
    0.06
    conti
    0.06
    Act Density 0.001%

    No Known Activations