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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verwaltung
    -0.07
     :</
    -0.07
    官方网站
    -0.07
    _RO
    -0.07
    _WR
    -0.07
    ブル
    -0.07
     πισ
    -0.07
    'à
    -0.07
     neighbour
    -0.07
     вра
    -0.07
    POSITIVE LOGITS
     vague
    0.10
     subjective
    0.09
     describes
    0.09
    describe
    0.08
     beskr
    0.08
    Описание
    0.08
     descriptions
    0.08
     gevoelens
    0.08
    描述
    0.08
     నాల
    0.08
    Act Density 0.002%

    No Known Activations