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

    Neuronpedia

    INDEX
    Explanations

    expressed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fail
    -0.08
     magnificent
    -0.07
    ollipop
    -0.06
     fine
    -0.06
    umbai
    -0.06
     STATS
    -0.06
    Slug
    -0.06
    .statistics
    -0.06
    capability
    -0.06
    _total
    -0.06
    POSITIVE LOGITS
     expressed
    0.09
     expresses
    0.08
     выраж
    0.08
     setIs
    0.07
    чення
    0.07
     yoğun
    0.07
     ความ
    0.07
    @(
    0.07
     melakukan
    0.06
    …"↵↵
    0.06
    Act Density 0.010%

    No Known Activations