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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ({})↵
    -0.07
    ]()
    -0.07
    роме
    -0.06
    *math
    -0.06
    Debug
    -0.06
     vero
    -0.06
     práv
    -0.06
     Вы
    -0.06
     kry
    -0.06
    Any
    -0.06
    POSITIVE LOGITS
    ;
    0.17
     ;
    0.12
    ”;
    0.11
    ;↵
    0.10
    );
    0.10
    ；
    0.09
    (';
    0.09
    _;
    0.09
    ;s
    0.09
    ؛
    0.09
    Act Density 0.382%

    No Known Activations