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

    Neuronpedia

    INDEX
    Explanations

    unpublished

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    葑
    -0.07
    廨
    -0.07
    _en
    -0.07
    \e
    -0.07
    副院长
    -0.06
     exquisite
    -0.06
    יי
    -0.06
    肴
    -0.06
    twig
    -0.06
    ɲ
    -0.06
    POSITIVE LOGITS
    .Tween
    0.07
    █
    0.07
    "github
    0.07
     div
    0.07
     property
    0.07
    גורם
    0.06
    .handle
    0.06
    :not
    0.06
     Rad
    0.06
     journalism
    0.06
    Act Density 0.002%

    No Known Activations