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

    Neuronpedia

    INDEX
    Explanations

    data analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     هاي
    -0.07
     educated
    -0.07
    XI
    -0.07
    �
    -0.06
     arada
    -0.06
     cornerstone
    -0.06
     stringWithFormat
    -0.06
    stacles
    -0.06
    =num
    -0.06
    xo
    -0.06
    POSITIVE LOGITS
     Apple
    0.07
     Networks
    0.07
     ارزش
    0.07
    発表
    0.06
     ISIL
    0.06
     Magick
    0.06
     MouseButton
    0.06
     They
    0.06
    }).
    0.06
    $model
    0.06
    Act Density 0.334%

    No Known Activations