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

    Neuronpedia

    INDEX
    Explanations

    conversational language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puss
    -0.26
    cce
    -0.25
    amac
    -0.25
    äºĨèĩªå·±çļĦ
    -0.24
    amenti
    -0.24
    createClass
    -0.24
    ä¸įå¦Ĥ
    -0.24
    å§Ķä¼ļ
    -0.24
     pals
    -0.24
    ç«Ł
    -0.24
    POSITIVE LOGITS
     mankind
    0.33
     society
    0.30
    western
    0.28
     humanity
    0.28
     Rare
    0.28
    å½ĵ代
    0.27
     worldwide
    0.27
     Worldwide
    0.27
    åħ¨ç¤¾ä¼ļ
    0.26
     contemporary
    0.26
    Act Density 0.002%

    No Known Activations