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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Risk
    -0.07
    workflow
    -0.07
     racked
    -0.06
    modification
    -0.06
    _zoom
    -0.06
    512
    -0.06
     xlabel
    -0.06
    _DELTA
    -0.06
    equal
    -0.06
     Truman
    -0.06
    POSITIVE LOGITS
     brightly
    0.07
     Unreal
    0.06
    ikon
    0.06
    histoire
    0.06
    силь
    0.06
     پي
    0.06
     torchvision
    0.06
    erli
    0.06
    etSocketAddress
    0.06
    ografia
    0.06
    Act Density 0.018%

    No Known Activations