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

    Neuronpedia

    INDEX
    Explanations

    research paper citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CLOSE
    -0.07
    كه
    -0.07
     Semester
    -0.07
    膳食
    -0.07
    ega
    -0.07
     ni
    -0.07
    身邊
    -0.07
    "class
    -0.07
     courseId
    -0.07
    证监会
    -0.06
    POSITIVE LOGITS
    要说
    0.08
    בול
    0.08
    iframe
    0.07
    簠
    0.07
    ITOR
    0.07
    하자
    0.06
    Tumblr
    0.06
    <Box
    0.06
     contentView
    0.06
    ants
    0.06
    Act Density 0.034%

    No Known Activations