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

    Neuronpedia

    INDEX
    Explanations

    Stanford

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    扫黑除
    -0.07
     tackling
    -0.07
    雞
    -0.07
    🄸
    -0.06
     transparency
    -0.06
     %.
    -0.06
    UCCESS
    -0.06
     reap
    -0.06
    	Py
    -0.06
    (requestCode
    -0.06
    POSITIVE LOGITS
     veículo
    0.06
    ']);↵↵
    0.06
    (segment
    0.06
    \\\\
    0.06
    .toString
    0.06
    =headers
    0.06
     Stanford
    0.06
     Safari
    0.06
     svg
    0.06
     XD
    0.06
    Act Density 0.001%

    No Known Activations