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

    Neuronpedia

    INDEX
    Explanations

    Describing cities' features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    双方
    -0.09
     পক্ষ
    -0.08
    VX
    -0.08
    COPE
    -0.08
     Klasse
    -0.08
     operands
    -0.08
    .matmul
    -0.08
    .Comment
    -0.08
     nhóm
    -0.08
     ARTICLE
    -0.08
    POSITIVE LOGITS
     관광
    0.14
     vibrant
    0.14
     inhabitants
    0.13
     bustling
    0.13
     tourism
    0.13
     atrações
    0.13
     touristique
    0.13
     attractions
    0.13
     picturesque
    0.12
     문화
    0.12
    Act Density 0.208%

    No Known Activations