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

    Neuronpedia

    INDEX
    Explanations

    mentions of buildings and their parts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kebun
    -0.66
     straff
    -0.65
    built
    -0.62
     nicio
    -0.60
    ctez
    -0.58
    isDebugEnabled
    -0.58
     getWidth
    -0.57
     nivå
    -0.57
    LEVEL
    -0.57
    ByteBuffer
    -0.57
    POSITIVE LOGITS
    Buildings
    0.91
     незавершена
    0.88
     Buildings
    0.87
    mobileqq
    0.84
     BUILDINGS
    0.81
     buildings
    0.80
    loài
    0.69
    buildings
    0.69
     Scrooge
    0.69
    RectangleBorder
    0.66
    Act Density 0.009%

    No Known Activations