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

    Neuronpedia

    INDEX
    Explanations

    managing requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .loader
    -0.07
    :w
    -0.07
    졌다
    -0.07
     Pasta
    -0.06
     cómo
    -0.06
     erhalten
    -0.06
    (document
    -0.06
    网贷
    -0.06
     Firstly
    -0.06
     Raptors
    -0.06
    POSITIVE LOGITS
    -driver
    0.07
    ┲
    0.07
    混
    0.07
     surprised
    0.07
    分布式
    0.07
    �
    0.06
     border
    0.06
    ?family
    0.06
     moral
    0.06
    三個
    0.06
    Act Density 0.022%

    No Known Activations