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

    Neuronpedia

    INDEX
    Explanations

    references to detention camps or facilities

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

    complex or sprawling structures and areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    illotine
    -0.38
    句
    -0.35
     Room
    -0.35
     Vitamin
    -0.35
    Vitamin
    -0.34
     psych
    -0.34
     font
    -0.33
     onver
    -0.33
    ApiController
    -0.33
    fär
    -0.33
    POSITIVE LOGITS
     complexo
    1.13
     complex
    1.08
     complejo
    1.05
     kompleks
    0.99
     sprawling
    0.98
    complex
    0.98
     complexe
    0.97
     complesso
    0.95
     complexes
    0.94
     komplex
    0.94
    Act Density 0.049%

    No Known Activations