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

    Neuronpedia

    INDEX
    Explanations

    references to local community and personal relationships

    oai_token-act-pair · gemini-2.0-flash

    neighborhoods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    featureID
    -0.43
    čem
    -0.39
    SourceChecksum
    -0.39
     ModelExpression
    -0.38
     sta
    -0.33
    ็น
    -0.33
    尼
    -0.33
     поз
    -0.32
     N
    -0.32
    outé
    -0.32
    POSITIVE LOGITS
     locality
    1.27
     localities
    1.07
     neighbourhood
    1.07
     neighborhood
    1.02
     region
    1.01
     village
    1.00
     town
    0.97
     Locality
    0.94
     neighbourhoods
    0.94
     지역
    0.93
    Act Density 1.271%

    No Known Activations