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

    Neuronpedia

    INDEX
    Explanations

    drinking glasses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     estimates
    -0.07
     investigate
    -0.07
    亮丽
    -0.07
    о
    -0.06
    证实
    -0.06
     masked
    -0.06
    mensaje
    -0.06
    炼
    -0.06
    _miss
    -0.06
     servlet
    -0.06
    POSITIVE LOGITS
     Yelp
    0.07
     cords
    0.07
    怩
    0.07
    赒
    0.07
    Ẻ
    0.06
    merged
    0.06
    aspberry
    0.06
     Remove
    0.06
    (sum
    0.06
    communication
    0.06
    Act Density 0.027%

    No Known Activations