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

    Neuronpedia

    INDEX
    Explanations

    references to structures and influences associated with power and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    vast concepts and scale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.49
    PhysRevLett
    -0.48
     noDo
    -0.47
     ujednoznacz
    -0.44
    weiss
    -0.44
    vician
    -0.43
     reloadData
    -0.43
    Veter
    -0.42
    rzost
    -0.42
    🔕
    -0.42
    POSITIVE LOGITS
     empire
    0.70
     giant
    0.58
     gigantic
    0.52
    empire
    0.52
     sprawling
    0.52
     vast
    0.51
     Empire
    0.51
     huge
    0.50
     gigantes
    0.50
     gigante
    0.49
    Act Density 0.180%

    No Known Activations