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

    Neuronpedia

    INDEX
    Explanations

    comparisons and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doctor
    -0.07
    西安市
    -0.06
    ﮫ
    -0.06
     simp
    -0.06
    Website
    -0.06
    imators
    -0.06
     super
    -0.06
     xhr
    -0.06
    .viewer
    -0.06
     website
    -0.06
    POSITIVE LOGITS
     persönlich
    0.08
    руб
    0.07
    expérience
    0.07
     plung
    0.07
    Вы
    0.07
    玩笑
    0.07
    振动
    0.07
     못
    0.07
    0.07
    inese
    0.07
    Act Density 0.138%

    No Known Activations