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

    Neuronpedia

    INDEX
    Explanations

    metal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rad
    -0.06
     стратег
    -0.06
    _sink
    -0.06
    _SQL
    -0.06
    ル
    -0.06
     resignation
    -0.06
    aren
    -0.06
     BOX
    -0.06
     crude
    -0.06
     odio
    -0.06
    POSITIVE LOGITS
     edeb
    0.07
     Invest
    0.07
     Miguel
    0.07
    xDF
    0.06
    pecial
    0.06
    efined
    0.06
    チャ
    0.06
     Understanding
    0.06
     cub
    0.06
    ----------</
    0.06
    Act Density 0.001%

    No Known Activations