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

    Neuronpedia

    INDEX
    Explanations

    Russian language and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twisted
    -0.07
     Wohnung
    -0.07
    _fitness
    -0.07
     Four
    -0.06
     Warsaw
    -0.06
    그래
    -0.06
     serialized
    -0.06
     Vault
    -0.06
     Warfare
    -0.06
     gravitational
    -0.06
    POSITIVE LOGITS
    (Point
    0.06
     }));↵
    0.06
     DisplayName
    0.06
     اتفاق
    0.06
    {name
    0.06
     '{"
    0.06
    .appspot
    0.06
    PointCloud
    0.06
    Associ
    0.06
     pony
    0.06
    Act Density 0.068%

    No Known Activations