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

    Neuronpedia

    INDEX
    Explanations

    Mental disorder research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narcotics
    -0.07
     WHERE
    -0.07
     cận
    -0.07
    INFO
    -0.07
    tember
    -0.06
     surprise
    -0.06
    도로
    -0.06
     watts
    -0.06
     widget
    -0.06
     keys
    -0.06
    POSITIVE LOGITS
     مطال
    0.07
    클
    0.06
     Exiting
    0.06
    ****
    0.06
     osm
    0.06
    (jScrollPane
    0.06
    入
    0.06
     सह
    0.06
    /im
    0.06
     thu
    0.06
    Act Density 0.041%

    No Known Activations