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

    Neuronpedia

    INDEX
    Explanations

    Fifth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    дел
    -0.08
    �
    -0.07
    driver
    -0.07
    臂
    -0.07
    AML
    -0.07
    해야
    -0.07
    .Tasks
    -0.07
    inning
    -0.07
    chip
    -0.07
     stranded
    -0.06
    POSITIVE LOGITS
    (rawValue
    0.08
     Paris
    0.07
     Sü
    0.07
    מדינה
    0.07
    []);↵
    0.07
     RDF
    0.07
     ''
↵
    0.07
    每年
    0.07
    {}]
    0.07
    [];
↵
    0.07
    Act Density 0.003%

    No Known Activations