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

    Neuronpedia

    INDEX
    Explanations

    PropTypes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    classList
    -0.07
     Bison
    -0.07
    yyy
    -0.07
     certains
    -0.07
    aternity
    -0.07
     circumstances
    -0.07
     Pens
    -0.07
    paragus
    -0.07
     Vander
    -0.07
     pancreatic
    -0.07
    POSITIVE LOGITS
    州区
    0.08
     כמו
    0.08
     עוב
    0.08
    \">";↵
    0.07
    จาก
    0.07
    ----------↵
    0.07
    固化
    0.07
     intermediary
    0.07
    ”—
    0.07
    ﯙ
    0.07
    Act Density 0.002%

    No Known Activations