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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unlaw
    -0.07
     neboť
    -0.07
     presents
    -0.07
     chip
    -0.07
    stoi
    -0.06
     subtle
    -0.06
    _active
    -0.06
     hardware
    -0.06
     covenant
    -0.06
    宇
    -0.06
    POSITIVE LOGITS
    Raises
    0.07
     서울특별시
    0.06
    ')↵↵↵↵
    0.06
     );↵↵↵
    0.06
     Lean
    0.06
     sluts
    0.06
    (serializer
    0.06
    ")]
↵
    0.06
     Lives
    0.06
     Renders
    0.06
    Act Density 0.088%

    No Known Activations