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

    Neuronpedia

    INDEX
    Explanations

    building

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     building
    -1.91
    building
    -1.91
     BUILDING
    -1.51
    Building
    -1.47
    BUILDING
    -1.47
     Building
    -1.41
    SourceChecksum
    -1.14
    builders
    -1.05
     builders
    -1.02
    buildings
    -0.97
    POSITIVE LOGITS
     Italiana
    0.45
     Negra
    0.44
    yatı
    0.44
    maries
    0.42
     joc
    0.42
    Estado
    0.42
     out
    0.41
    ähkö
    0.41
     assai
    0.40
    Estadio
    0.40
    Act Density 0.050%

    No Known Activations