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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Charles
    -0.07
    Mitch
    -0.07
     Shirley
    -0.06
     hydraulic
    -0.06
    ర
    -0.06
     Nicole
    -0.06
    perhaps
    -0.06
     preliminary
    -0.06
    全力以赴
    -0.06
     eight
    -0.06
    POSITIVE LOGITS
     //↵↵
    0.07
     arasında
    0.07
    炸弹
    0.07
     Dai
    0.07
    結果
    0.06
    带回
    0.06
     Cards
    0.06
    瑑
    0.06
    iners
    0.06
     nghiệm
    0.06
    Act Density 0.021%

    No Known Activations