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

    Neuronpedia

    INDEX
    Explanations

    introductions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     米
    -0.07
      ↵  ↵
    -0.06
     credible
    -0.06
    steen
    -0.06
    .gb
    -0.06
     appoint
    -0.06
    фров
    -0.06
     Edward
    -0.06
    :
↵
    -0.06
     )
↵
↵
    -0.06
    POSITIVE LOGITS
     Des
    0.07
    ोड
    0.07
     가족
    0.06
     recieved
    0.06
     togg
    0.06
    CreatedAt
    0.06
    times
    0.06
     Soil
    0.06
     Correct
    0.06
    	Render
    0.06
    Act Density 0.067%

    No Known Activations