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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    以åıĬ
    -0.42
    æĸĩåĮĸåĴĮ
    -0.40
    管çIJĨåĴĮ
    -0.38
    åıĬ
    -0.37
    è´¨éĩıåĴĮ
    -0.37
    æĪĸæĺ¯
    -0.36
    æĪĸèĢħ
    -0.36
    以åıĬåħ¶ä»ĸ
    -0.36
     или
    -0.34
    ãģĬãĤĪãģ³
    -0.34
    POSITIVE LOGITS
     Mime
    0.29
     third
    0.29
    vation
    0.28
    çļĦæľĢåIJİä¸Ģ
    0.27
     ;↵↵↵
    0.26
    zej
    0.26
     hyper
    0.25
     Third
    0.25
    venth
    0.24
    aves
    0.24
    Act Density 0.038%

    No Known Activations