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

    Neuronpedia

    INDEX
    Explanations

    Random text/new document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    çľ¼éĩĮ
    -0.29
     ts
    -0.28
    (QL
    -0.27
    annon
    -0.27
     cultural
    -0.25
    aur
    -0.25
    sector
    -0.25
     spinning
    -0.25
    çľ¼ä¸Ń
    -0.24
    ursor
    -0.24
    POSITIVE LOGITS
    æĥ°
    0.26
    éģ´éĢī
    0.26
    èİ·
    0.25
    è°ĥæķ´
    0.24
     пÑĢоб
    0.24
    æŁIJä¸Ģ
    0.24
    調æķ´
    0.24
    ç¼ļ
    0.23
     Wor
    0.23
    ::<
    0.23
    Act Density 0.010%

    No Known Activations