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

    Neuronpedia

    INDEX
    Explanations

    grammatical/stylistic discussion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	dfs
    -0.07
     ()↵
    -0.06
     WRONG
    -0.06
    >");↵
    -0.06
    )"↵
    -0.06
    ccb
    -0.06
    pecific
    -0.06
     tiên
    -0.06
    ()));↵
    -0.06
     ，
    -0.06
    POSITIVE LOGITS
     Gn
    0.06
     nom
    0.06
    –and
    0.06
     intersection
    0.06
    .weixin
    0.06
    官方
    0.06
    azon
    0.06
     필
    0.06
     reviewed
    0.06
    Nova
    0.06
    Act Density 0.003%

    No Known Activations