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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     bé
    -0.08
     superhero
    -0.07
    .Areas
    -0.07
    🏩
    -0.07
    .Unsupported
    -0.07
    :text
    -0.07
     imu
    -0.07
    .htm
    -0.07
     DIRECT
    -0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.07
    POSITIVE LOGITS
    ی
    0.07
    енным
    0.07
    ^{-
    0.07
    咏
    0.07
    之作
    0.07
     favourite
    0.06
     comentario
    0.06
     защит
    0.06
    ߚ
    0.06
    etros
    0.06
    Act Density 0.025%

    No Known Activations