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

    Neuronpedia

    INDEX
    Explanations

    bos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [T
    -0.08
     над
    -0.07
    ᒡ
    -0.07
    [z
    -0.07
    Ẽ
    -0.07
    那就
    -0.07
    ])),↵
    -0.07
    "))↵
    -0.07
    国土
    -0.06
     sanctions
    -0.06
    POSITIVE LOGITS
     verbose
    0.07
    Tutorial
    0.07
     окол
    0.07
     пор
    0.07
     bos
    0.07
     Intermediate
    0.07
     serif
    0.07
    Sir
    0.07
     COMMENTS
    0.07
    .verbose
    0.07
    Act Density 0.002%

    No Known Activations