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

    Neuronpedia

    INDEX
    Explanations

    East Asian names and topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    黪
    -0.08
    འ
    -0.08
    <nav
    -0.07
    欧冠
    -0.07
    ;b
    -0.07
     masc
    -0.07
     bac
    -0.06
    пад
    -0.06
     }}"
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    (Logger
    0.07
     friends
    0.07
    其他国家
    0.07
    RICT
    0.07
    き
    0.07
    ,message
    0.07
     +
↵
    0.07
    .Ticks
    0.07
     ********
    0.06
     Californ
    0.06
    Act Density 0.040%

    No Known Activations