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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    羊肉
    -0.07
     Kushner
    -0.07
     apparent
    -0.07
    灭火
    -0.07
     Beard
    -0.07
    较大
    -0.07
     birds
    -0.07
    nelle
    -0.07
     Mah
    -0.06
    GG
    -0.06
    POSITIVE LOGITS
    .market
    0.08
    分销
    0.07
    Branch
    0.07
    (()=>
    0.07
    助长
    0.07
    社会各界
    0.07
     LA
    0.07
     seus
    0.07
    ?");↵
    0.07
    ["+
    0.07
    Act Density 0.030%

    No Known Activations