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

    Neuronpedia

    INDEX
    Explanations

    App

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Forest
    -0.06
     businessman
    -0.06
     grounds
    -0.06
    ]){
    -0.06
     package
    -0.06
     meanwhile
    -0.06
    _area
    -0.06
    illus
    -0.06
     facade
    -0.06
    {}]
    -0.06
    POSITIVE LOGITS
    789
    0.07
     etmiştir
    0.07
    acific
    0.06
    闲
    0.06
    crafted
    0.06
    렸
    0.06
    相關
    0.06
    rc
    0.06
    账
    0.06
     있었
    0.06
    Act Density 0.014%

    No Known Activations