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

    Neuronpedia

    INDEX
    Explanations

    expected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arap
    -0.07
    _locator
    -0.07
     Irr
    -0.06
    874
    -0.06
    うん
    -0.06
    .inst
    -0.06
     Incorrect
    -0.05
    _cost
    -0.05
     filters
    -0.05
    atics
    -0.05
    POSITIVE LOGITS
     retirement
    0.07
     ET
    0.07
    SVG
    0.07
    uber
    0.07
     tipped
    0.06
    vm
    0.06
     GAL
    0.06
     minX
    0.06
    .undefined
    0.06
    :CGRect
    0.06
    Act Density 0.005%

    No Known Activations